© 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. 142573
    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
    åĵªéĩĮ
    -0.27
    ighest
    -0.26
    oyal
    -0.26
    ä¸ĢåľĪ
    -0.26
    çļĦæľĢ大
    -0.25
    rieve
    -0.24
    nameof
    -0.24
     max
    -0.24
    _where
    -0.24
    æľĢå¤ļ
    -0.24
    POSITIVE LOGITS
     mandatory
    0.27
     respons
    0.26
     finals
    0.25
    .deb
    0.25
    ç¹¼
    0.25
    opsis
    0.25
    .getLog
    0.24
    alogy
    0.24
    没æľī
    0.24
     Mandatory
    0.23
    Activations Density 5.125%

    No Known Activations

    This feature has no known activations.