# Qwen 3.8 identifies games from neural network weights

> Simon Willison found that a laptop-running Qwen 3.8 27B identified three of four games from their network weights, without tools. Each answer took nearly an hour or longer.

Oossa · 2026-11-03 · https://oossa.com/en/qwen-3-8-identifies-games-from-neural-network-weights

Simon Willison tested whether Qwen 3.8 27B could identify a game by examining the raw weights of a small neural network, without running code or using other tools. Running the 17GB model on his laptop, he says it correctly identified Pac-Man, Pong and Breakout, but mistook Freeway for a Pac-Man-like game.

The successful answers took 46 minutes to more than an hour each. Willison’s experiment tests interpreting weights; it does not show Qwen editing or improving another model, a separate claim explored in the paper he was following.

## The facts

- Qwen 3.8 27B correctly identified 3 of 4 game networks in Willison’s tests.
- The Pac-Man answer took 46 minutes and 12 seconds; the Pong answer took 1 hour, 4 minutes and 54 seconds.

## Why it matters

For people running large models locally, the test suggests they may be able to infer what a small network does from its weights, though it was slow and failed on one of four games.

## Sources & references

1. [Qwen 3.8 27B on my laptop can interpret model weights, too](https://simonwillison.net/2026/Nov/3/qwen-can-interpret-model-weights/) – Simon Willison, 2026-11-03

Last updated: 2026-11-03