© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41726
    Prev
    Next
    INDEX
    Explanations

    Arab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    á»Ń
    -0.29
     kh
    -0.27
    å±Ī
    -0.27
    éŃĶ鬼
    -0.27
    æľ¬ç½ijç«Ļ
    -0.27
     mapping
    -0.25
    ä¸įè¿ľ
    -0.25
    å¸ĸ
    -0.25
    æ¾ľ
    -0.24
    mapping
    -0.24
    POSITIVE LOGITS
    çĵ·
    0.26
    æĹłè¾ľ
    0.26
    ä½Ĩå®ĥ
    0.25
    ota
    0.25
    OTA
    0.24
     Eternal
    0.24
     UPDATE
    0.24
     Editor
    0.24
    OptionsResolver
    0.24
     Tonight
    0.24
    Activations Density 2.350%

    No Known Activations