interpretability

October 17, 2026

• Goodfire argues neural networks may be more interpretable than assumed

  Goodfire reports 99–100% single-feature behavior in a retrained vision model and a small unexplained share in Qwen3-32B; the site presents this as a hypothesis, not settled science.

  99–100% reported single-feature behavior90% Qwen3-32B neurons with one main job, reported2–4% unexplained share, reported

  interpretabilityresearchmodels