© 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. 87004
    Prev
    Next
    INDEX
    Explanations

    function words

    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
    建ç«ĭ
    -0.30
    malink
    -0.29
    建ç«ĭèµ·
    -0.26
    keiten
    -0.26
    Establish
    -0.26
     establishing
    -0.26
    alom
    -0.26
     establish
    -0.26
    hani
    -0.24
    ç´¯
    -0.24
    POSITIVE LOGITS
     Season
    0.27
    igg
    0.27
    season
    0.25
    èĥ½æĬĬ
    0.25
    uku
    0.25
    _season
    0.25
    _CPP
    0.24
     Ñģезон
    0.24
     season
    0.24
    Season
    0.24
    Activations Density 0.010%

    No Known Activations