© 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. 33437
    Prev
    Next
    INDEX
    Explanations

    policy or principle

    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
    ä¸İæĸ¹æ³ķ
    -0.08
    çļĦ带é¢Ĩä¸ĭ
    -0.08
    çļĦç§įç±»
    -0.08
    rupt
    -0.08
    ossip
    -0.08
    åĴĮæĸ¹æ³ķ
    -0.08
    æīĢåģļ
    -0.08
    ико
    -0.08
    acock
    -0.08
    resse
    -0.08
    POSITIVE LOGITS
     principle
    0.09
    åİŁåĪĻ
    0.09
     principles
    0.07
     slogan
    0.07
    æĸ¹éĴĪ
    0.06
    imum
    0.06
     mentality
    0.06
    å¼ıçļĦ
    0.06
     Principle
    0.06
    cott
    0.06
    Activations Density 0.121%

    No Known Activations