© 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. 33-TRANSCODER-HP
    7. 54807
    Prev
    Next
    INDEX
    Explanations

    Species range/habitats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    spot
    -0.27
    uffles
    -0.26
    uetooth
    -0.25
     educators
    -0.25
     disposition
    -0.25
    çĨ
    -0.25
     rings
    -0.25
     ranges
    -0.25
    .eth
    -0.25
    ç»ĵ
    -0.24
    POSITIVE LOGITS
    åģľä¸ĭ
    0.27
    æķ´ä¸ª
    0.27
    ç²ī
    0.26
    æĹłç¼ĺ
    0.26
    åģľä¸ĭæĿ¥
    0.26
    our
    0.25
     HttpServlet
    0.25
    æ¯ķç«Ł
    0.24
    æľīæŶåĢĻ
    0.24
    aka
    0.24
    Activations Density 0.004%

    No Known Activations