© 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. 61357
    Prev
    Next
    INDEX
    Explanations

    Fourier analysis

    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
    ç©¿éĢı
    -0.08
     contrario
    -0.08
    ãĥ«ãĤ¯
    -0.08
    èĻļ空
    -0.08
    رة
    -0.07
    uté
    -0.07
    çİĦå¹»å°ı说
    -0.07
    稳åģ¥
    -0.07
     ëĸ¨ìĸ´
    -0.07
    onger
    -0.07
    POSITIVE LOGITS
    åĤħ
    0.09
     Fourier
    0.08
     discontin
    0.08
     sine
    0.08
    æŁ¯
    0.07
    ((-
    0.07
    strip
    0.07
    ä¾Ľæļĸ
    0.07
    ä¸Ĭ岸
    0.07
     alternating
    0.06
    Activations Density 0.015%

    No Known Activations