# hijohnnylin/neuronpedia

open source interpretability platform 🧠

Repository: https://github.com/hijohnnylin/neuronpedia
Canonical: https://ross.abutalabs.com/products/neuronpedia
Homepage: https://neuronpedia.org
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: ai, interpretability
Last push: 2026-09-03T02:01:23+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 83
- inputs: {"age_days": 1169, "days_push": 0, "days_rel": 0, "gap_med": 0.0, "n_releases_24m": 825}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1124, forks 147 (observed 2026-09-03T02:15:12.705473+00:00)

## What it is
Neuronpedia is an open source AI interpretability platform for exploring, visualizing, and steering the internals of language models. It hosts terabytes of sparse autoencoder (SAE) feature data, activation dashboards, circuit tracing, autointerp explanations, and a JSON API, both as a hosted site (neuronpedia.org) and a self-hostable webapp.

## Use cases
- browse sparse autoencoder features of language models
- search which SAE features activate on my text
- visualize neuron activations and top logits for a feature
- embed an interpretability feature dashboard in my site or paper
- steer an LLM's behavior using feature vectors
- trace a model's internal reasoning with circuit graphs
- find misaligned persona features in open-weight models
- query feature data programmatically via a JSON API

## When to choose
- you do mechanistic interpretability research on LLMs and need feature/SAE dashboards
- you want a hosted or self-hosted browsable database of activations and autointerp explanations
- you need embeddable visualizations of model internals for papers or demos
- you want to test features on custom text or steer models via an API

## When to avoid
- you need general-purpose ML training or fine-tuning tooling
- you want a lightweight library rather than a full web platform with a database
- your work doesn't involve inspecting neural network internals
- you need offline tooling without running inference infrastructure

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, data-visualization, search-engine, api-framework, llm-inference, rag
- domain: artificial-intelligence, machine-learning, large-language-models, data-visualization, developer-tools
- platform: self-hosted
- tags: interpretability, mechanistic-interpretability, sparse-autoencoders, sae, neuron-visualization, feature-dashboards, activation-analysis, circuit-tracing, autointerp, steering, llm-internals, open-source-platform, web-server, nodejs, typescript, docker

## Member repositories
- hijohnnylin/neuronpedia (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:12.705473+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:11.896418+00:00, confidence not recorded.
  - readme: https://github.com/hijohnnylin/neuronpedia (fetched 2026-09-03T02:15:12.705473+00:00, sha 4fba8047ceb6)
  - homepage: https://neuronpedia.org (fetched 2026-08-29T12:45:15.526856+00:00, sha 92d01aed1ab5)
  - site_page: https://docs.neuronpedia.org/features (fetched 2026-08-29T12:45:15.535952+00:00, sha d6f9d07fe1ec)
  - site_page: https://docs.neuronpedia.org/search (fetched 2026-08-29T12:45:15.540858+00:00, sha bf67df87ebce)
  - site_page: https://docs.neuronpedia.org/lists (fetched 2026-08-29T12:45:15.542338+00:00, sha 3a0c9428682e)
  - site_page: https://docs.neuronpedia.org/embed-iframe (fetched 2026-08-29T12:45:15.544137+00:00, sha b784fb727f45)
  - registry_npm: https://registry.npmjs.org/neuronpedia (fetched 2026-08-29T12:45:15.545730+00:00, sha b7c514fccea2)
  - site_page: https://www.neuronpedia.org/misaligned-persona (fetched 2026-08-29T12:45:15.537768+00:00, sha 7c21d4c61780)
  - site_page: https://www.neuronpedia.org/gpt2sm-apollojt (fetched 2026-08-29T12:45:15.539372+00:00, sha 575e19a5bf6a)
- Data as of 2026-08-30T08:39:29.467469+00:00.