Transformers
sparse-autoencoder
sae
interpretability
deception
sandbagging
topk
mechanistic-interpretability
Instructions to use Solshine/deception-v4-saes-qwen3-0p6b-base-v4mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Solshine/deception-v4-saes-qwen3-0p6b-base-v4mixed with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Solshine/deception-v4-saes-qwen3-0p6b-base-v4mixed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Welcome to the community
The community tab is the place to discuss and collaborate with the HF community!