© 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. 41644
    Prev
    Next
    INDEX
    Explanations

    present day

    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
    åľ¨åݻ年
    -0.08
    åݻ年åIJĮæľŁ
    -0.08
     recently
    -0.08
    hiri
    -0.08
    Recently
    -0.08
    æ¯Ķåݻ年
    -0.08
    ä¸īå¹´åīį
    -0.08
    _latest
    -0.08
     recientemente
    -0.07
    .insertBefore
    -0.07
    POSITIVE LOGITS
     later
    0.15
     today
    0.14
    åIJİæĿ¥çļĦ
    0.14
    æĹ¥åIJİ
    0.13
    åIJİæĿ¥
    0.13
    ä»ĬæĹ¥
    0.13
    ä»Ĭ天
    0.13
    ä»Ĭ天çļĦ
    0.13
    ä»ĬæĹ¥çļĦ
    0.12
    later
    0.12
    Activations Density 0.354%

    No Known Activations