© 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. 10192
    Prev
    Next
    INDEX
    Explanations

    numbers preceding dots

    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
    ее
    -0.07
    ?key
    -0.07
    oin
    -0.07
    ibly
    -0.07
    Ỽ
    -0.06
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.06
    ine
    -0.06
    umble
    -0.06
    ãģĿ
    -0.06
    á»Ŀ
    -0.06
    POSITIVE LOGITS
    lix
    0.08
    æĽ´æĸ°æĹ¥æľŁ
    0.08
    ements
    0.07
    astra
    0.07
    quets
    0.07
     createAction
    0.07
    缸è¾ħ缸æĪIJ
    0.07
     Clarkson
    0.07
     rouge
    0.07
    ଶ
    0.07
    Activations Density 0.002%

    No Known Activations