© 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. 25872
    Prev
    Next
    INDEX
    Explanations

    Indicative, possession, life, education

    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
     either
    -0.07
    æĹłè®ºæĺ¯åľ¨
    -0.07
    Either
    -0.07
    ueux
    -0.07
    renc
    -0.07
    æĻĵ举
    -0.07
     Either
    -0.07
    ä¸ĩ家
    -0.07
    either
    -0.06
    æĥ£
    -0.06
    POSITIVE LOGITS
    该æ¡Ī
    0.09
     ìĿ´ì²ĺëŁ¼
    0.08
    æѤ类
    0.08
    æľ¬æ¡Īä¸Ń
    0.08
    à¹ģà¸ļà¸ļà¸Ļีà¹ī
    0.08
    åľ¨æŃ¤æ¬¡
    0.08
     подобнÑĭе
    0.08
    à¸ŀั
    0.07
    opil
    0.07
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.07
    Activations Density 0.199%

    No Known Activations