© 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. 14506
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    elaar
    -0.10
    ative
    -0.07
    Ñĸд
    -0.07
    éķ¿æŀª
    -0.07
    uation
    -0.07
    haw
    -0.07
    ¸
    -0.07
    ieÃŁ
    -0.07
    awy
    -0.07
    ikov
    -0.07
    POSITIVE LOGITS
    gether
    0.10
    ä»Ģä¹Īæĺ¯
    0.08
    ìķ¼
    0.07
    æĤ¨åı¯èĥ½
    0.06
    å®ĥæīĢ
    0.06
    æĹ¥åŃIJéĩĮ
    0.06
    enade
    0.06
     "
    0.06
    tems
    0.06
    erÃŃa
    0.06
    Activations Density 0.015%

    No Known Activations