© 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. 61494
    Prev
    Next
    INDEX
    Explanations

    body temperature and brain signals

    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
    éħĹ
    -0.08
    éĽĨä¸ŃéļĶ离
    -0.08
    æŃ»ä¸į
    -0.07
    æĤ¨æīĢåľ¨çļĦä½įç½®
    -0.07
    ä¸įèĥ½ä½ľä¸º
    -0.07
     holdings
    -0.07
    æĹłæĤĶ
    -0.07
    æĪĸéĿŀ
    -0.07
    ä¸įèĥ½æ»¡è¶³
    -0.07
    RACT
    -0.07
    POSITIVE LOGITS
    ç»ı绾
    0.08
    罢工
    0.08
    mph
    0.08
    æİĴæ¯Ĵ
    0.07
    åĪĨæ³Į
    0.07
    åIJĦåı¸
    0.07
     momentarily
    0.07
     brain
    0.07
    æ´»è·ĥ度
    0.07
    è´Łè´£
    0.07
    Activations Density 0.114%

    No Known Activations