A local Qwen model can read neural-network weights
Qwen 3.8 27B running on a laptop can interpret raw neural-network weights, showing that weight-space programming is not limited to the paper’s frontier-model example. The weights are just floating-point numbers describing a model, and the model is asked to infer what they do without tools or code execution. The writeup also separates that ability from using code to edit and improve another model.