© 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. 20-TRANSCODER-HP
    7. 129022
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     unspecified
    -0.27
    Translated
    -0.27
    ä¸ĢæĿ¡é¾Ļ
    -0.27
     undocumented
    -0.27
    gone
    -0.26
     translated
    -0.26
    çIJĩ
    -0.25
    doc
    -0.25
     Mits
    -0.24
     doc
    -0.24
    POSITIVE LOGITS
    ä¸įä¸ĭ
    0.27
    á»ĩt
    0.24
    PUR
    0.23
    åħ¥ãĤĮ
    0.23
    à¸İ
    0.23
    ãĥĭãĥ¼
    0.23
    çªĹåı£
    0.23
     Ñģв
    0.23
    ÙĪÙĤ
    0.23
    ãģĦãģı
    0.22
    Activations Density 9.325%

    No Known Activations

    This feature has no known activations.