© 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. 32-TRANSCODER-HP
    7. 40902
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    setDisplay
    -0.28
    .unshift
    -0.26
     most
    -0.25
    tee
    -0.24
    nung
    -0.24
    ijn
    -0.24
    ië
    -0.23
     Redistribution
    -0.23
     Bend
    -0.23
    æľĢå¤ļ
    -0.23
    POSITIVE LOGITS
    沧
    0.31
     Query
    0.29
    query
    0.29
    åIJĥ
    0.29
     query
    0.28
    æŁ¥è¯¢
    0.27
    åIJĥå®Į
    0.27
    _query
    0.27
    =query
    0.27
    .query
    0.27
    Activations Density 0.001%

    No Known Activations