Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University