© 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. 64554
    Prev
    Next
    INDEX
    Explanations

    oscillating, cyclic, alternating, sinusoidal

    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
    æĹłæĢ¨
    -0.07
     пÑĢедел
    -0.07
     ÙħÙĪÙĤÙģ
    -0.06
    .blur
    -0.06
    ä¹ĭè¨Ģ
    -0.06
    amal
    -0.06
    èįŁ
    -0.06
     pessim
    -0.06
    teles
    -0.06
    丹éĿĴ
    -0.06
    POSITIVE LOGITS
    åij¨æľŁ
    0.16
    åij¨æľŁæĢ§
    0.15
     cycle
    0.13
    åij¨æľŁçļĦ
    0.13
    .cycle
    0.12
     cycles
    0.12
    -cycle
    0.12
    _cycle
    0.12
     periodic
    0.11
    (period
    0.11
    Activations Density 0.102%

    No Known Activations