Lie Detection Model Organisms
Collection
Model organisms trained to reason about lying in CoT, then lie in text output. • 17 items • Updated
Uploaded model
- Developed by: ai-safety-institute
- License: apache-2.0
- Finetuned from model : Qwen/Qwen3.5-27B
This qwen3_5 model was trained 2x faster with Unsloth
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ai-safety-institute/Qwen3.5-27B-eval_sandbagger
Base model
Qwen/Qwen3.5-27B
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ai-safety-institute/Qwen3.5-27B-eval_sandbagger", dtype="auto")