# Dongxi NLP asks how sparse rewiring differs from weight space programming

> Original title: 很酷！但是 sparse rewiring 又跟所谓的 weight space progmming 有什么分别。

- Source: Dongxi NLP
- Published: 2026-11-12T10:15:18.000Z
- Bad Influence: https://badinfluence.news/items/d054299ln0dfwl6c0zmzf242s
- Original: https://x.com/dongxi_nlp/status/2120822738650550744

## Summary

Dongxi NLP says Sparse Rewiring, which Max Sloef reports, trains 89 of Qwen3-8B's 442,368 neurons to make an owl persona that matches full SFT. Dongxi NLP asks how this differs from so-called weight space programming, and says interpretability researchers should pay attention.

## Post

很酷！但是 sparse rewiring 又跟所谓的 weight space progmming 有什么分别。

可以确定的，做可解释性 LLM 的研究员，春天来了。

依然推荐阅读！感兴趣的，把 post 直接扔给 agent 解读！

## Quoted post @maxsloef

> Finetuning changes all model weights, even when learning a simple behavior. Can we make that change interpretable?
> 
> Yes! Sparse Rewiring learns new triggers for neurons, not new outputs. Training just 89 of Qwen3-8B's 442,368 neurons makes an owl persona that matches full SFT!

https://x.com/maxsloef/status/2120545170873823742