© 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. 8602
    Prev
    Next
    INDEX
    Explanations

    game theory

    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
    edig
    -0.07
    ÙĤا
    -0.07
    Portal
    -0.07
    icket
    -0.06
    èĸª
    -0.06
    è¿ĻäºĽæķ°æį®
    -0.06
    æĹħå±ħ
    -0.06
    /runtime
    -0.06
    _kill
    -0.06
    йд
    -0.06
    POSITIVE LOGITS
    é»ĺå¥ij
    0.12
    ç»Ļ对æĸ¹
    0.11
    åįļå¼Ī
    0.09
     selfish
    0.09
    å½¼æѤçļĦ
    0.09
    ilater
    0.09
    äºĴåĪ©
    0.09
    åIJĦèĩª
    0.08
    ãģĬäºĴ
    0.08
     unilateral
    0.08
    Activations Density 0.007%

    No Known Activations