© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32247
    Prev
    Next
    INDEX
    Explanations

    `/*` followed by code or `.h`

    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
    #{@
    -0.08
    Configurer
    -0.07
    æ¶Īæģ¯ç§°
    -0.07
    èħ°çº¿
    -0.07
     [=[
    -0.07
    çĤ¹åĩ»å¤įåĪ¶éĵ¾æİ¥
    -0.07
    _setopt
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    åľ¨å¿ħ
    -0.07
    Ī
    -0.07
    POSITIVE LOGITS
    æĺ¥æ±Ł
    0.07
    奮
    0.07
    ä¸Ī
    0.06
    ä¼ı
    0.06
    heb
    0.06
    ieg
    0.06
    女çļĩ
    0.06
    вил
    0.06
    æĦıè¯ĨåĴĮ
    0.06
    ï½ŀãĢĤ
    0.06
    Activations Density 0.282%

    No Known Activations