© 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. 41789
    Prev
    Next
    INDEX
    Explanations

    Non-profit/taxes

    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
    deen
    -0.29
    ilde
    -0.28
    itage
    -0.28
    éĿ¢åħ·
    -0.27
    omba
    -0.27
    keiten
    -0.27
    åı¯ä»¥çĽ´æİ¥
    -0.26
     Aspect
    -0.26
    缴æİ¥
    -0.26
    tem
    -0.25
    POSITIVE LOGITS
     "','
    0.27
    Êİ
    0.26
    /libs
    0.26
    <cv
    0.25
    æĪIJ为äºĨ
    0.25
    åĬĽåº¦
    0.25
    é«ĺçŃīéĻ¢æł¡
    0.25
     institutional
    0.24
    stitution
    0.23
    ãĥ±
    0.23
    Activations Density 0.969%

    No Known Activations