© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57030
    Prev
    Next
    INDEX
    Explanations

    documentation and manuals

    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
    éĶĢåĶ®ä¸ļ绩
    -0.08
    ãĥ¼ãĥĹ
    -0.07
    ª
    -0.07
    ئÙĥ
    -0.07
    nemonic
    -0.07
    æľĢèijĹåIJįçļĦ
    -0.07
    andalone
    -0.07
    еÑģÑĤвÑĥ
    -0.06
    redi
    -0.06
     Famous
    -0.06
    POSITIVE LOGITS
     stip
    0.08
    è¦ģæ±ĤçļĦ
    0.08
    ä¸Ģçķª
    0.07
     says
    0.07
    è¦ģæ±Ĥ
    0.07
    æĮĩåĩº
    0.07
    _REQUIRE
    0.07
    æĿ¡æĿ¡
    0.07
    Float
    0.07
    ç¼¥
    0.07
    Activations Density 0.013%

    No Known Activations