© 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. 17790
    Prev
    Next
    INDEX
    Explanations

    Military ranks/army

    np_max-act-logits · gemini-2.0-flash
    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
    anes
    -0.27
    ène
    -0.27
    uell
    -0.27
    ensch
    -0.26
    èµ°
    -0.25
     borderTop
    -0.25
    yen
    -0.25
    ç±»åŀĭ
    -0.24
     presidency
    -0.24
    porte
    -0.24
    POSITIVE LOGITS
    íĥĿ
    0.28
    çīĪæĿĥ声æĺİ
    0.28
    latin
    0.28
    leigh
    0.26
    æ¯Ķè¾ĥé«ĺ
    0.25
    ä¸ĢåĽ¢
    0.25
    ilet
    0.25
     heartbeat
    0.24
    ç§ĺè¯Ģ
    0.24
    ÑĢаÑĦ
    0.24
    Activations Density 0.134%

    No Known Activations