ComfyUI Node
Feature Map
Decompose conditioning through a Sparse Autoencoder to see which interpretable features are active. Use the feature indices shown here to drive the Feature Gate node.
Feature Map
- conditioning
- VISUALIZATION
- FEATURES
◄sae_path►
◄top_k30►
◄sae_expansion8►
◄transcoder_repo►
◄pool_modeper_token►
◄dict_path►
CategoryConcept Steer/Features
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| conditioning | CONDITIONING | — | |
| sae_path | STRING | Absolute path to SAE weights (.pt file). Train one with 'Train Lens (SAE)' using --sae-save, or from the lens_factory CLI. | |
| top_k | INT | 305–100 | Number of top features to display |
| sae_expansion | INT | 82–128 | SAE expansion factor (auto-detected for transcoders). 8x for trained SAEs, 64x for pretrained transcoders. |
| transcoder_repo | STRING | HuggingFace repo for pretrained transcoders (e.g. 'mwhanna/qwen3-4b-transcoders'). Auto-downloads ~1.7GB layer file on first use. Leave empty to use sae_path instead. | |
| pool_mode | COMBO | per_token | How to handle token activations before SAE encoding. 'per_token' = encode each token individually (matches SAE training), 'mean' = average tokens then encode (fast but less accurate), 'max' = max activation per feature across tokens |
| dict_path | STRING | Path to feature dictionary JSON (from Feature Dictionary node). When provided, features are labeled with what they respond to. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| VISUALIZATION | IMAGE | — |
| FEATURES | STRING | — |