© 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. 43922
    Prev
    Next
    INDEX
    Explanations

    yl

    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
    Not in Any Lists

    No Comments

    Negative Logits
    py
    -0.27
     life
    -0.27
    æĸ°æł¼å±Ģ
    -0.27
    è´¢
    -0.26
    à¹ĥ
    -0.26
    itti
    -0.25
     py
    -0.25
    isers
    -0.25
     MON
    -0.25
    Life
    -0.25
    POSITIVE LOGITS
     Ñĥдален
    0.27
    .mi
    0.27
    imir
    0.26
     CDDL
    0.26
    heap
    0.26
    Ñħа
    0.25
    UGE
    0.25
    ìĦĿ
    0.25
    hot
    0.24
    /XML
    0.24
    Activations Density 0.003%

    No Known Activations