© 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. 30-TRANSCODER-HP
    7. 95144
    Prev
    Next
    INDEX
    Explanations

    Culture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĨĽäºĭ
    -0.42
    éĩijèŀį
    -0.41
     aviation
    -0.40
     medical
    -0.39
     gardening
    -0.39
     financial
    -0.36
    åĮ»åѦ
    -0.36
    é£Łåĵģ
    -0.35
     Agricultural
    -0.35
     football
    -0.34
    POSITIVE LOGITS
    æĸĩåĮĸ
    0.59
     culture
    0.57
    æĸĩåĮĸ建设
    0.54
     Culture
    0.53
     cultural
    0.53
    æĸĩåĮĸçļĦ
    0.50
    æĸĩåĮĸåĴĮ
    0.49
    çļĦæĸĩåĮĸ
    0.47
     Cultural
    0.45
    Culture
    0.42
    Activations Density 0.894%

    No Known Activations