© 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. 31-TRANSCODER-HP
    7. 17736
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åİŁåŀĭ
    -0.30
     electr
    -0.28
    ulos
    -0.28
    omore
    -0.28
    æŀľ
    -0.27
    ä¸ĢåŃĹ
    -0.27
    -shadow
    -0.27
    влад
    -0.26
     california
    -0.25
    å½±
    -0.25
    POSITIVE LOGITS
    æľºåĻ¨
    0.29
     rel
    0.28
    eks
    0.27
    ãģĺ
    0.27
    >Main
    0.26
     willen
    0.25
     notch
    0.25
    éĻ¢åī¯éĻ¢éķ¿
    0.25
    multipart
    0.25
    é»ĺé»ĺ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.