© 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. 13647
    Prev
    Next
    INDEX
    Explanations

    generic, general, typical

    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
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.10
    ாத
    -0.08
    磶
    -0.08
    峪
    -0.08
    arend
    -0.08
    个æĸ¹éĿ¢
    -0.08
    ernity
    -0.08
    æľīè¯Ŀ
    -0.08
    á»Ļt
    -0.07
     allegedly
    -0.07
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.08
    æĥħæ³ģä¸ĭ
    0.08
     бÑĭваеÑĤ
    0.08
    çĬ¶æĢģä¸ĭ
    0.07
    æĿ¡ä»¶ä¸ĭ
    0.07
    ken
    0.07
    èĥĮæĻ¯ä¸ĭ
    0.07
    çļĦæĥħåĨµä¸ĭ
    0.06
    å¦į
    0.06
    éĻª
    0.06
    Activations Density 0.051%

    No Known Activations