# A two-neuron steering recipe removes most refusals from Alibaba's Qwen3.5-4B, and an independent replication confirms it

The replication measured refusals falling from 90% to 8% on a 4 GB graphics card, with no gradient computation and no training data.

- Published: 2026-10-27T06:18:03.036Z
- Canonical: https://polylog.news/ai/2026-10-27/a-two-neuron-steering-recipe-removes-most-refusals-from-alib
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

On October 24, an interpretability researcher who posts on X as lyra published an activation-steering recipe for Qwen3.5-4B, a small open-weight model from Alibaba. The recipe adjusts one neuron up in layer 14 and one down in layer 13. The…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-27/a-two-neuron-steering-recipe-removes-most-refusals-from-alib (subscription information: https://polylog.news/pricing).