© 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. 19490
    Prev
    Next
    INDEX
    Explanations

    game periods

    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
    次年
    -0.08
     yearly
    -0.08
    æ¯ıå¹´
    -0.08
     someday
    -0.08
    转载请
    -0.08
     annually
    -0.07
    attel
    -0.07
    æĹºåŃ£
    -0.07
     jährlich
    -0.07
     ежегодно
    -0.07
    POSITIVE LOGITS
     minutes
    0.09
     минÑĥÑĤ
    0.08
    idget
    0.08
     minutos
    0.08
    minutes
    0.08
     Ðŀбо
    0.07
    ä¸ĬæĿ¥
    0.07
    å¼Ģå±Ģ
    0.07
    _minutes
    0.07
    ä¸Ģ个å°ıæŶ
    0.07
    Activations Density 0.234%

    No Known Activations