© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĶåŃIJ
    -0.27
    æĢ»è£ģ
    -0.25
    _stub
    -0.25
    ungi
    -0.25
    è´´
    -0.24
     Chancellor
    -0.24
    xit
    -0.24
     zro
    -0.24
    chine
    -0.23
    æĮ«
    -0.23
    POSITIVE LOGITS
    æľ¬ç½ijç«Ļ
    0.26
    åı¯è§Ĩ
    0.25
    æľ¬æľŁ
    0.25
    æ·±åħ¥å¼Ģå±ķ
    0.24
    ç¯Ģ
    0.24
    sdale
    0.24
     echoing
    0.24
    èĬĤ
    0.23
    åĨ¤
    0.23
    èĭ¦èĭ¦
    0.23
    Activations Density 0.176%

    No Known Activations

    This feature has no known activations.