© 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. 108676
    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
    omm
    -0.28
    棰
    -0.27
    æ²¥
    -0.27
     à¸ļาà¸Ĺ
    -0.26
    inkel
    -0.26
     Mast
    -0.25
     Phase
    -0.25
     redeemed
    -0.24
    brtc
    -0.24
     overlaps
    -0.24
    POSITIVE LOGITS
    ç½¢
    0.33
     overnight
    0.28
    æĤłæĤł
    0.27
    .named
    0.27
     foss
    0.26
    OTS
    0.26
    opot
    0.25
    WAR
    0.24
     again
    0.24
    æıIJåıĸ
    0.24
    Activations Density 49.109%

    No Known Activations

    This feature has no known activations.