© 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. 25114
    Prev
    Next
    INDEX
    Explanations

    Chinese characters followed by specific nouns

    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
    åĴĮ
    -0.11
    人
    -0.10
    çļĦ
    -0.09
    ÙĨ
    -0.09
    æľī
    -0.09
    ìĿĺ
    -0.09
    ت
    -0.08
    ä¸Ģ
    -0.08
    ãģĬ
    -0.08
    ת
    -0.07
    POSITIVE LOGITS
     Insg
    0.10
    åĬ©äºİ
    0.09
    swith
    0.09
     Fór
    0.09
    çļĦä¸Ģå®ļ
    0.09
    éĥ¨çļĦ
    0.09
    bies
    0.09
    à§įস
    0.09
     Ejem
    0.09
    ìį¨
    0.09
    Activations Density 0.008%

    No Known Activations