© 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. 129293
    Prev
    Next
    INDEX
    Explanations

    question and answer texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cean
    -0.29
     ÑĢеалÑĮно
    -0.25
    uely
    -0.25
    溢价
    -0.24
    ean
    -0.24
    çİ°å®ŀä¸Ń
    -0.24
    åįĬå¤ľ
    -0.24
    ocide
    -0.24
    oky
    -0.23
    ç§ijæĬĢåĽŃ
    -0.23
    POSITIVE LOGITS
    fdc
    0.29
    _TUN
    0.27
    ä¸įåIJĮç¨ĭ度
    0.26
    pré
    0.26
    encies
    0.25
     Kang
    0.25
     kang
    0.24
     Knox
    0.23
     glean
    0.23
    grave
    0.23
    Activations Density 0.004%

    No Known Activations