© 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. 20-TRANSCODER-HP
    7. 62835
    Prev
    Next
    INDEX
    Explanations

    male pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çļĦ妻åŃIJ
    -0.35
    /she
    -0.35
    çĪ¶åŃIJ
    -0.32
     stesso
    -0.32
     koji
    -0.30
    кÑĢÑĭл
    -0.30
    åĴĮä»ĸçļĦ
    -0.29
    妻åŃIJ
    -0.28
     himself
    -0.28
    ç²¾åŃIJ
    -0.28
    POSITIVE LOGITS
     herself
    0.44
    å¨ĺ家
    0.42
    女士
    0.37
    /he
    0.35
    å«ģç»Ļ
    0.35
     ÙĨÙģسÙĩا
    0.34
    esy
    0.33
    ела
    0.31
    å«ģ
    0.30
     administrative
    0.28
    Activations Density 58.593%

    No Known Activations