Products

Transformer-circuits

The Interpretability team strives to change that — to understand these models to better plan for a future of safe AI.

transformer-circuits.pub Writing & Documents / Academic Writing & Research

AI Benchmark
Desktop
Mobile
Monthly visits
150.1K
Down8.7%MoMOct 2026
Public revenue
Undisclosed
No public revenue evidence yet
Entry price
Free
No monthly subscription pricing
Launched
24mo ago
2024-11-21 · Est.

Traffic

Monthly visitsData through Oct 2026
Events4 changes

Marketing moves

Launches, search & content, referrals, promotions
  • Launched on Show HN (579 pts · 99 comments)Launch

    Llama 3.2 Interpretability with Sparse Autoencoders — I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability resear…

    Nov 21, 2024 · 24mo agoLaunch page

Third-party reviews & case dossiers

Acquisition breakdowns, engineer reviews & open-source metrics
Show HN
2024-11-21Source
Post excerpt:
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for

Traffic sources

Oct 2026

Traffic breakdown

Channels

  • Direct54%
  • Referrals18%
  • Organic Search17%
  • Social7%
  • Other3%

Countries

  • United States55%
  • Germany7%
  • Brazil6%
  • United Kingdom5%
  • India5%

Search

Domain authority —Domain registered 2021-12-08

KeywordMonthly volume
toy models of superposition2,120
a mathematical framework for transformer circuits870
on the biology of a large language model580
j space j lens400
toy model of superposition paper160

Traffic data: Vaneform

Pricing

Pricing page not identified yet, or no public pricing listed.

Pages & changes

Tracked since 2026-11-04

Key pages

Weekly snapshots
Home
transformer-circuits.pub/ Snapshot 2026-11-06

Changes

  1. Nov 1 · 14d ago

    Adopted technology: CloudflareFeatures

    —→Cloudflare

    At the time: 150.1K visits/mo3 concurrent moves
  2. Nov 1 · 14d ago

    Adopted technology: Cloudflare Bot ManagementFeatures

    —→Cloudflare Bot Management

    At the time: 150.1K visits/mo3 concurrent moves
  3. Nov 1 · 14d ago

    Adopted technology: HubSpotFeatures

    —→HubSpot

    At the time: 150.1K visits/mo3 concurrent moves
  4. Nov 1 · 14d ago

    Adopted technology: RSSFeatures

    —→RSS

    At the time: 150.1K visits/mo3 concurrent moves

Design

First-screen visual analysis & :root CSS

Minimal Monochrome (Light canvas, airy density) featuring centered headline + cta layout and illustration / character art visuals.

First-screen preview · click to zoom

First-screen pitch & conversion flow

“Anthropic’s Interpretability Research”

Centered Headline + CTA hero structure paired with direct input / instant try CTA and no explicit trust bar.

Conversion path: Centered Headline + CTA + Illustration / Character Art → Direct Input / Instant Try

Palette · click to copy

5-D design score7.4 / 10
Typography
8.0
Color & Contrast
7.0
Layout & Spacing
8.0
Craft & Polish
7.0
Distinctiveness
7.0

Structure

Fonts
Styrene A / system-ui
Primary visual
Illustration / Character Art
Social proof
No Explicit Trust Bar
Navigation
Minimal Logo + Action
Theme & density
Light · Airy
Corners & depth
Medium Radius · Hairline borders
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Minimal Monochrome (with Editorial)

Monochrome palette with a single accent color, hairline dividers, and generous whitespace.

## Design Tokens

```css
:root {
  --background: #faf9f5;
  --surface: #eeede9;
  --foreground: #000000;
  --muted-foreground: #0f0f0e;
  --accent: #0000ee;
  --radius: 8px;
  --font-heading: "Styrene A", ui-sans-serif, system-ui, sans-serif;
  --font-body: "system-ui", ui-sans-serif, system-ui, sans-serif;
}
```

Color area ratio: Background #FAF9F5 (~74%) · Surface #EEEDE9 (~15%) · Text #000000 (~6%) · Muted Text #0F0F0E (~4%) · Accent #0000EE (~1%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.

## Layout & Conversion Structure

- Hero layout: Centered Headline + CTA
- Navigation: Minimal Logo + Action
- Theme & density: Light · Airy
- Border radius & elevation: Medium Radius; no drop shadows—separate layers with hairline borders and whitespace
- Primary visual medium: Illustration / Character Art
- Conversion CTA: Direct Input / Instant Try
- Headline hook: Category Positioning Anchor
- Hero components: Custom Illustration
- Spatial layout notes: Centered Headline + CTA hero structure paired with direct input / instant try CTA and no explicit trust bar.
- Visual summary: Minimal Monochrome (Light canvas, airy density) featuring centered headline + cta layout and illustration / character art visuals.

## Avoid

- Multi-stop neon gradients
- Heavy drop shadows
- More than one competing accent color

Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.

Questions & evidence

How much website traffic does Transformer-circuits get?
Vaneform estimates 150.1K website visits in 2026-10. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
What is Transformer-circuits and what platforms does it support?
Transformer-circuits is catalogued under Academic Writing & Research: The Interpretability team strives to change that — to understand these models to better plan for a future of safe AI.. Supported platforms: Web.

Related products in this category

Writing & Documents / Academic Writing & Research

These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.