© 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. 112924
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific contexts

    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
    侧éĿ¢
    -0.30
     mund
    -0.28
    仪
    -0.25
    //
    -0.24
    orted
    -0.24
    requ
    -0.24
    ç¯ĩ
    -0.24
     ters
    -0.24
    TAG
    -0.23
    éĺĩ
    -0.23
    POSITIVE LOGITS
    DownList
    0.32
    ULA
    0.29
    åľ¨ä¸ŃåĽ½
    0.27
    ilian
    0.26
     Holt
    0.26
    tempts
    0.26
    .choices
    0.25
    å¾Ģ
    0.25
    pivot
    0.25
    кова
    0.25
    Activations Density 0.007%

    No Known Activations