© 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. 62653
    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
     kitt
    -0.31
    åĪ°ä½į
    -0.28
    æĸ¹éĿ¢çļĦ
    -0.26
    fram
    -0.25
    åĥıæĺ¯
    -0.25
    çĵ¶é¢Ī
    -0.24
     observ
    -0.24
    çľĭä¸įåĪ°
    -0.24
     anybody
    -0.24
     zeit
    -0.24
    POSITIVE LOGITS
    æĪĺ
    0.28
    ç«ĭæ¡Ī
    0.28
    UsageId
    0.27
    代è¨Ģ
    0.26
    -live
    0.23
    å¾·å°Ķ
    0.23
    AGIC
    0.23
    èĢģ人家
    0.23
    enal
    0.23
    .live
    0.22
    Activations Density 9.004%

    No Known Activations

    This feature has no known activations.