© 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. 39925
    Prev
    Next
    INDEX
    Explanations

    kind of / type of

    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
    è¿Ļæĺ¯ä¸ª
    -0.09
    æł¹æį®ä¸įåIJĮçļĦ
    -0.08
    loat
    -0.08
    è¿Ļ个åĵģçīĮ
    -0.08
     hereby
    -0.08
    urator
    -0.08
    iso
    -0.08
    çŃīåIJĦæĸ¹éĿ¢
    -0.07
    Iso
    -0.07
    /options
    -0.07
    POSITIVE LOGITS
    è¿Ļç±»
    0.13
    æѤ类
    0.12
    è¿Ļç§į
    0.12
     подобнÑĭе
    0.11
    éĢĻé¡ŀ
    0.09
    ä¸Ģç±»
    0.09
     подобнÑĭÑħ
    0.09
    è¿Ļæł·çļĦ
    0.09
    ä¹ĭç±»
    0.09
     Such
    0.08
    Activations Density 0.271%

    No Known Activations