© 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. 19785
    Prev
    Next
    INDEX
    Explanations

    the

    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
     cla
    -0.25
    éĤ£æł·çļĦ
    -0.25
    éĤ£äºº
    -0.25
    æ°ijå¿ĥ
    -0.25
    è¿Ļç§įæĥħåĨµ
    -0.24
    çªĿ
    -0.24
    éĤ£ä¸ªäºº
    -0.24
    éĤ£å°±æĺ¯
    -0.24
    人身
    -0.24
    ati
    -0.24
    POSITIVE LOGITS
     point
    0.75
    çĤ¹
    0.58
     Point
    0.57
     begin
    0.57
    _point
    0.56
    Point
    0.55
    point
    0.55
    å¼Ģå§ĭ
    0.54
     beginning
    0.52
     start
    0.52
    Activations Density 0.228%

    No Known Activations