© 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. 30915
    Prev
    Next
    INDEX
    Explanations

    grounded theory and deductions

    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
    ä¸įå±¥è¡Į
    -0.07
     vest
    -0.07
    achat
    -0.07
    Queryable
    -0.07
     competit
    -0.07
    _managed
    -0.07
    ä¸ĩ人æ°ijå¸ģ
    -0.07
    æĮī计åĪĴ
    -0.07
     obstacle
    -0.07
    (answer
    -0.07
    POSITIVE LOGITS
    å½Ĵ纳
    0.14
     extrapol
    0.13
    æıIJçĤ¼
    0.12
     conclusions
    0.12
    æݨæĸŃ
    0.11
    å¾ĹåĩºçļĦ
    0.11
    å¾Ĺåĩº
    0.11
     deductions
    0.11
    ç»ĵ论
    0.11
    å¾Ĺåĩºç»ĵ论
    0.10
    Activations Density 0.010%

    No Known Activations