© 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. 37553
    Prev
    Next
    INDEX
    Explanations

    because / cause

    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
    Negative Logits
    èĢĮä»ĸçļĦ
    -0.09
    elling
    -0.09
    inary
    -0.09
    neur
    -0.08
    avings
    -0.08
    èĢĮè¿ĩ
    -0.08
    Mua
    -0.08
    åĽłä¸ºä»ĸ们
    -0.08
    omain
    -0.08
    çļĦä¸Ģå®ļ
    -0.08
    POSITIVE LOGITS
    ç§įç§įåİŁåĽł
    0.10
    æĪij们æľī
    0.09
    ÑģÑı
    0.09
    åIJĦç§įåİŁåĽł
    0.09
    ãģ¨ãģĦãģ£ãģ¦
    0.08
    å®ĥæĺ¯
    0.08
    ê»ı
    0.08
    “
    0.07
    è¿Ļæĺ¯
    0.07
    ÅĽ
    0.06
    Activations Density 0.001%

    No Known Activations