© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25112
    Prev
    Next
    INDEX
    Explanations

    high school, girls, boys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľĢä½İåѦåİĨ
    -0.09
    ouched
    -0.08
    å©´å¹¼åĦ¿
    -0.08
    å©´åĦ¿
    -0.08
    æµĨ
    -0.08
    ingin
    -0.08
    客ä½ĵ
    -0.08
    æĸ°çĶŁåĦ¿
    -0.07
    示æĦı
    -0.07
    uple
    -0.07
    POSITIVE LOGITS
    å¯Ħ宿
    0.08
    girls
    0.07
    à¸Ľà¸¥à¸²à¸¢
    0.07
     girls
    0.07
    èĭ±æīį
    0.07
     boys
    0.07
    ëĵ±íķĻêµIJ
    0.07
     Salut
    0.07
    æĸĩçIJĨ
    0.07
     Girls
    0.07
    Activations Density 0.210%

    No Known Activations