© 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. 22-TRANSCODER-HP
    7. 131117
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĶ¯éĺŁ
    -0.27
    ä»ĸ们ä¼ļ
    -0.27
    ropri
    -0.26
    ingly
    -0.25
    ä¼ļåľ¨
    -0.25
    ä¼ļ使
    -0.24
     Treasurer
    -0.23
    ãģķãģ¾ãģĸãģ¾
    -0.23
    æ·±åħ¥æİ¨è¿Ľ
    -0.23
    è¡Įä¸ļåįıä¼ļ
    -0.23
    POSITIVE LOGITS
     zip
    0.29
     bil
    0.28
    aff
    0.28
    zip
    0.27
    commons
    0.26
     Kob
    0.25
    ÃŃst
    0.24
    ä¼į
    0.24
     ran
    0.24
    c
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.