© 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. 19416
    Prev
    Next
    INDEX
    Explanations

    arbitrarily, further, indefinitely, graded, smaller, unlimited

    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¬ç¯ĩæĸĩç«ł
    -0.08
    afari
    -0.08
    ëįľ
    -0.08
    nich
    -0.08
     dönÃ¼ÅŁ
    -0.07
    né
    -0.07
    满满
    -0.07
    ä¸įå¹²
    -0.07
    è®´
    -0.07
    доÑĢа
    -0.07
    POSITIVE LOGITS
     arbitrarily
    0.08
     Ñĥгодно
    0.07
    esor
    0.07
     impun
    0.07
    PointSize
    0.07
    éĻª
    0.07
    ç¨ĭ度çļĦ
    0.06
    åĢįçļĦ
    0.06
     imaginable
    0.06
     independently
    0.06
    Activations Density 0.004%

    No Known Activations