© 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. 86883
    Prev
    Next
    INDEX
    Explanations

    News snippets

    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
     lect
    -0.27
    lection
    -0.25
     Fired
    -0.25
    åľ¨ç¾İåĽ½
    -0.25
    åľ¨æĹ¥æľ¬
    -0.25
     before
    -0.23
    CV
    -0.23
    lexer
    -0.23
    ä¸ĸçķĮä¸Ĭ
    -0.23
     Gund
    -0.23
    POSITIVE LOGITS
    fä
    0.28
    è²Į
    0.27
    /vnd
    0.27
    âĦ¯
    0.26
    ês
    0.26
    obutton
    0.26
    nown
    0.24
    arÃŃa
    0.24
    IGIN
    0.24
    rstrip
    0.23
    Activations Density 0.004%

    No Known Activations