© 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. 22-TRANSCODER-HP
    7. 97067
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åľ¨é¦Ļ港
    -0.35
    åľ¨çİ°åľº
    -0.35
    åľ¨æ¸¸æĪıä¸Ń
    -0.34
    åľ¨æķ´ä¸ª
    -0.33
    åľ¨è¿ĩåİ»
    -0.32
    åľ¨åĽ½åĨħ
    -0.32
     regarding
    -0.30
    åľ¨åħ¨åĽ½
    -0.29
    åľ¨è¿Ļ个
    -0.29
    åľ¨ä¸ŃåĽ½
    -0.29
    POSITIVE LOGITS
    éĤ¸
    0.31
    æĮ¤åİĭ
    0.30
    åĢŃ
    0.28
    ingham
    0.27
    [^
    0.27
    TS
    0.26
    åıªæľī
    0.25
     æĹ¥
    0.25
    ley
    0.24
    èµ°
    0.24
    Activations Density 0.005%

    No Known Activations