© 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. 22-TRANSCODER-HP
    7. 97272
    Prev
    Next
    INDEX
    Explanations

    Web

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    uld
    -0.29
    -comm
    -0.29
    createClass
    -0.28
     comm
    -0.26
    rail
    -0.25
    sty
    -0.25
     Tart
    -0.25
    hest
    -0.25
    (comm
    -0.25
    ald
    -0.24
    POSITIVE LOGITS
    Ĺ
    0.26
    Advertisements
    0.25
    æĬĢæľ¯æľįåĬ¡
    0.23
    zelf
    0.23
    iendo
    0.23
    ание
    0.23
    帶
    0.23
    _im
    0.22
     indeed
    0.22
    From
    0.22
    Activations Density 0.011%

    No Known Activations