© 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. 44185
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    omedical
    -0.26
    $
    -0.25
    èŁł
    -0.25
    competitive
    -0.24
    {}
    -0.24
    çĽĺ
    -0.24
     Maduro
    -0.24
    {
    -0.24
    ason
    -0.24
    ${
    -0.24
    POSITIVE LOGITS
    —"
    0.38
    —is
    0.36
     "**
    0.34
     '**
    0.33
    âĶĢâĶĢ
    0.32
     ðĿ
    0.32
    —a
    0.32
    —to
    0.31
     _______,
    0.31
    —it
    0.31
    Activations Density 0.003%

    No Known Activations