© 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. 59117
    Prev
    Next
    INDEX
    Explanations

    foreign words or preceding text

    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
    mue
    -0.09
    ateway
    -0.07
    acap
    -0.07
    ÑıÑĤÑĮ
    -0.07
    åľ¨æĪij们
    -0.07
    åĿIJçĿĢ
    -0.07
     boyun
    -0.06
    æ³ķè¯Ń
    -0.06
    дÑĢ
    -0.06
    heet
    -0.06
    POSITIVE LOGITS
    åIJĮæł·çļĦ
    0.08
     précédent
    0.08
    åīįè¿°
    0.08
    ä¸Ģæł·çļĦ
    0.07
    ä¸Ģæł·
    0.07
     poprzed
    0.07
    ãģ¨åIJĮãģĺ
    0.07
    缸åIJĮçļĦ
    0.07
    ä¸Ģæł·äºĨ
    0.07
     vorige
    0.07
    Activations Density 0.267%

    No Known Activations