© 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. 20-TRANSCODER-HP
    7. 142554
    Prev
    Next
    INDEX
    Explanations

    varied text sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ìľ¡
    -0.27
    è§Ħ
    -0.25
    èĻIJ
    -0.25
    주ìĿĺ
    -0.24
    etri
    -0.24
    çģµæ´»
    -0.24
     ==
    -0.24
    _choose
    -0.23
    ä¸įåı¯éģ¿åħį
    -0.23
    =%.
    -0.23
    POSITIVE LOGITS
    å°±åľ¨äºİ
    0.28
    檫
    0.27
     Weston
    0.27
    ä¸ĢæĹı
    0.26
    æѤç§į
    0.26
    æĹ¥åľ¨
    0.25
    ><!--
    0.24
    ıè¿°
    0.24
    laden
    0.24
    .named
    0.24
    Activations Density 15.094%

    No Known Activations