© 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. 19650
    Prev
    Next
    INDEX
    Explanations

    math expression fragments

    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
    satz
    -0.08
    ä¹ĭæĢ¥
    -0.08
     ЯÑĢо
    -0.07
    ikuti
    -0.07
    istribution
    -0.07
    uable
    -0.07
    ذاÙĥ
    -0.07
    zie
    -0.07
    testdata
    -0.07
    -fashioned
    -0.07
    POSITIVE LOGITS
    ersistent
    0.08
    ãģ¿ãģ¤
    0.08
    inhos
    0.07
    кÑĢов
    0.07
    æĹłéĤª
    0.07
    mdi
    0.07
    ãĤĪãģĨãģ«ãģªãĤĭ
    0.07
    iscop
    0.07
    游æĪıç½ij
    0.07
    empla
    0.07
    Activations Density 0.087%

    No Known Activations