© 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. 18-TRANSCODER-HP
    7. 88396
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trident
    -0.29
    onas
    -0.28
    %m
    -0.27
    çĿ¨
    -0.26
     Witnesses
    -0.25
    hardware
    -0.25
    æĤ¨çļĦåŃ©åŃIJ
    -0.25
    ,opt
    -0.25
    aminer
    -0.24
    _sun
    -0.24
    POSITIVE LOGITS
    ember
    0.29
    FAIL
    0.25
    åĩ»
    0.24
    çĥŃæIJľ
    0.24
    ished
    0.24
     affili
    0.24
    çŁ¿å±±
    0.24
    ç©´
    0.23
    ä¸Ģå¼Ģå§ĭå°±
    0.23
    à¸Ńà¸ļ
    0.23
    Activations Density 2.131%

    No Known Activations

    This feature has no known activations.