© 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. 18009
    Prev
    Next
    INDEX
    Explanations

    normal

    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
    è¢Ń
    -0.28
     increment
    -0.27
    uously
    -0.26
    æĽ´å¤ļ精彩
    -0.26
     AUTHORS
    -0.25
     Eventually
    -0.25
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.25
    stant
    -0.25
    alogy
    -0.25
    -main
    -0.24
    POSITIVE LOGITS
     normal
    0.72
    æŃ£å¸¸
    0.61
    æŃ£å¸¸çļĦ
    0.60
    normal
    0.58
     NORMAL
    0.57
     Normal
    0.57
    _normal
    0.54
    Normal
    0.53
    -normal
    0.52
    (normal
    0.52
    Activations Density 17.899%

    No Known Activations