© 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. 129227
    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
    å¾Ĺä½ı
    -0.26
    asco
    -0.26
    åıĹçĽĬ
    -0.26
    人æ°ijæľįåĬ¡
    -0.25
    ä½ıäºĨ
    -0.24
    æıĨ
    -0.23
    flen
    -0.23
    /meta
    -0.23
    alta
    -0.23
     cu
    -0.23
    POSITIVE LOGITS
    mad
    0.27
     TimeSpan
    0.25
     Milit
    0.25
    .Timeout
    0.25
    æµģ失
    0.24
    ç«
    0.24
    ç«¥
    0.24
     gấp
    0.24
    屿
    0.24
    dots
    0.23
    Activations Density 0.420%

    No Known Activations

    This feature has no known activations.