© 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. 22633
    Prev
    Next
    INDEX
    Explanations

    design patterns, templates, axioms, hints

    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
    缮ä¸Ń
    -0.08
    ä¸įéķ¿
    -0.07
    _utils
    -0.07
    ÃģN
    -0.07
    quisa
    -0.07
    orada
    -0.07
    请ä¸ĭè½½
    -0.06
    emis
    -0.06
    ((__
    -0.06
    yed
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įä¸ľè¥¿
    0.08
    plural
    0.08
    iae
    0.08
     коÑĤоÑĢÑĭми
    0.08
    å¤ļç§įå¤ļæł·
    0.07
    åĩĿ
    0.07
    çļĦç§įç±»
    0.07
    _SHARED
    0.07
    æ
    0.07
    äººä»¬åľ¨
    0.07
    Activations Density 0.066%

    No Known Activations