LocalLLaMA/Qwen3-0.6B-golden-gate-bridge
Text Generation • Updated • 1
Runtime steering vectors for local models that work with MLX and PyTorch through PTS, with the data behind them.
Note Turn Golden Gate Bridge mentions up or down in Qwen3-0.6B.
Note Stops Qwen3.5-0.8B repeating itself while thinking.
Note Prompts with measured mention rates, used to find the Golden Gate vectors.