© 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. 1459
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with x and t

    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
    æľ¬æĸĩæĿ¥èĩª
    -0.08
    oop
    -0.07
    oor
    -0.07
    á»ı
    -0.07
    ضÙĬ
    -0.07
    otos
    -0.07
    åı£éķĩ
    -0.07
    noinspection
    -0.07
    ä¹ĭåĪĥ
    -0.07
    иÑĤо
    -0.07
    POSITIVE LOGITS
    acas
    0.07
    éħī
    0.07
    arez
    0.07
    Ļ
    0.07
    ervals
    0.07
    cour
    0.06
    úst
    0.06
    Äħtek
    0.06
    æ°Ĺãģ«ãģªãĤĭ
    0.06
    Radio
    0.06
    Activations Density 0.003%

    No Known Activations