© 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. 41171
    Prev
    Next
    INDEX
    Explanations

    coding and specific terms

    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
    SharedPtr
    -0.08
    plib
    -0.07
    ä¸ĭæŬ
    -0.07
    گاÙĩÛĮ
    -0.07
    ãģ¾ãģĹãģ¦
    -0.06
    )[:
    -0.06
    GameData
    -0.06
    çŃīçĸ¾çĹħ
    -0.06
    IVAL
    -0.06
    .Roll
    -0.06
    POSITIVE LOGITS
    ä¹Łå¥½
    0.09
    ä¹Łç½¢
    0.08
    鬼
    0.07
    วà¸Ļ
    0.07
    çļĦè¿ĺæĺ¯
    0.07
    ä¸Ģç§įæĺ¯
    0.07
    ãĢģ
    0.07
    EGI
    0.07
    å¼ıåĴĮ
    0.07
    à¸ģà¹ĩà¸Ķี
    0.07
    Activations Density 0.738%

    No Known Activations