© 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. 20022
    Prev
    Next
    INDEX
    Explanations

    what to wear/gift

    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
    ggia
    -0.07
    ļĮ
    -0.07
    å¤ĸéĥ¨
    -0.07
    æĬĹ
    -0.07
    undur
    -0.07
    bre
    -0.07
     External
    -0.07
    æ¯ı个åŃ©åŃIJ
    -0.07
    åĸĺæģ¯
    -0.07
    WISE
    -0.07
    POSITIVE LOGITS
     etiquette
    0.10
    æľī礼
    0.08
     politely
    0.08
     Etiqu
    0.07
    _OVERRIDE
    0.07
     guidelines
    0.07
    åľºåIJĪ
    0.07
    è¿ĩå¾Ĺ
    0.07
     rules
    0.07
     Ñĥва
    0.07
    Activations Density 0.018%

    No Known Activations