1lyramakesmusic / neuron-explorerSteering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the resultsinterpretabilitymechanistic-interpretabilityqwensteeringPythonMIT1.9K total226 forks+740 starsfrom 1,062 · score 6.61
2google-deepmind / detectorscopeBuild AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)ai-text-detectionexplainable-aiinterpretabilitymechanistic-interpretabilitysparse-autoencodersPythonAPACHE-2.0360 total32 forks+299 starsfrom 9 · score 5.70