© 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. 140691
    Prev
    Next
    INDEX
    Explanations

    psychological, behavioral studies

    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
    ochen
    -0.29
    oyal
    -0.28
     privately
    -0.28
    ç§ģèĩª
    -0.25
     Mueller
    -0.25
    LERÄ°
    -0.25
     legally
    -0.25
    icensing
    -0.25
    åĺĺ
    -0.24
    åĮĹ京æŶéĹ´
    -0.24
    POSITIVE LOGITS
    ä¸į足
    0.30
    å©ī
    0.29
    çݰ代
    0.29
    vik
    0.28
    wick
    0.28
    黼
    0.28
     poi
    0.26
    ç¥ŀç»ı
    0.26
    è¡Į
    0.26
    lene
    0.26
    Activations Density 14.709%

    No Known Activations