Trace every feature. Every circuit. Every second of reasoning. Open source interpretability that researchers, students, and safety teams can actually use — on their phone, in their papers, in their deployments.
qwen36-27b-sae-multilayer · 3 TopK SAEs, L11/L31/L55qwen36-27b-sae-papergrade · n=65k, AuxK, 200M tokens (training)qwen36-deepconf-probe · +6pp SuperGPQA via PWMVqwen36-feature-circuits · honest negative resultNeuronpedia is the encyclopedia. OpenInterp is the microscope, the laboratory, the watchtower, and the school — one platform, four ways in.
See the model thinking, feature by feature, token by token. The narrative layer Neuronpedia lacks.
Edit the model. Compose interventions. Export steered checkpoints. Democratizes the "edit-the-model" capability that today lives in five labs.
Monitor LLMs in production. Feature-level observability for safety teams. The SaaS tier that sustains the entire OSS platform.
Onboard the world. From "what is an activation" to "discover a new feature" in 90 minutes. Education-first, not PhD-gated.
Watch Qwen3.6-27B reason through a clinical triage prompt. Tokens emerge. Features fire. Click any feature, adjust its strength, see the counterfactual. No feature page is static here — this is the story of the model's thought.
Neuronpedia gave the world its first SAE encyclopedia — a massive, essential contribution. But an encyclopedia is where you look things up. It's not where discovery happens, and it's not where a student becomes a contributor.
The gaps that no current tool fills:
| Gap | Symptom | Today |
|---|---|---|
| Narrative / trace | features shown in isolation, never the full journey of a prompt | nobody |
| Comparison | "why did model A answer X but B answer Y?" — activation diff | nobody |
| Circuits as UI | feature→feature flows live in papers, not tools | Anthropic (text only) |
| Onboarding | UX assumes PhD-level familiarity; students bounce | almost nobody |
| Failure archaeology | "my model hallucinated, which features fired?" → write a notebook | nobody |
OpenInterp is built on public, reproducible research shipped under MIT. Every claim has a repo:
1. Cross-model Rosetta Stone. A graph of feature equivalences across Qwen, Gemma, Llama, Claude, Mistral. It only grows. Years to replicate.
2. Watchtower revenue flywheel. B2B API revenue pays for the OSS tier. Neuronpedia has no business model — we can be free where it matters (students, researchers) and profitable where it sustains (Fortune 500 safety teams).
3. Model Partner Program. Agreements with Qwen, Gemma, Mistral to ship SAEs alongside every model release. "X launched with OpenInterp integration" becomes table stakes.
That's the north star. Everything — the hero animation, the mobile-first layout, the zero-login Trace Theater, the shareable trace URLs — is optimized toward that one scene.
Neuronpedia is a tab you consult. OpenInterp is a tab you leave open.
Each milestone ships something shippable. No vaporware, no roadmap promises without a prototype. Every quarter ends with a demo that someone uses.
Everything is MIT licensed. Every SAE is on HuggingFace. Every research step — including the failures — is public. If this vision matters to you, there are four ways in.