© 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. 30-TRANSCODER-HP
    7. 96803
    Prev
    Next
    INDEX
    Explanations

    discrimination/equal opportunity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     draws
    -0.35
    drawing
    -0.32
     Draws
    -0.32
    好人
    -0.30
     draw
    -0.30
     drawing
    -0.29
    (draw
    -0.28
     drew
    -0.28
    draw
    -0.28
    DRAW
    -0.27
    POSITIVE LOGITS
     on
    0.39
    'on
    0.30
    otic
    0.28
    æ³Ľ
    0.28
    æµģæĺŁ
    0.27
    piel
    0.27
     ME
    0.27
    ç¨ĭå¼ı
    0.27
    owski
    0.26
    æ°¾
    0.26
    Activations Density 0.887%

    No Known Activations