© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39664
    Prev
    Next
    INDEX
    Explanations

    range and level

    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
    ä¸įä¿Ĺ
    -0.08
    å¤Ł
    -0.07
    次äºİ
    -0.07
    æıIJåīį
    -0.06
    ardon
    -0.06
    äºĮè½®
    -0.06
    ä¼ĺèī¯
    -0.06
    强è¡Į
    -0.06
    ç´
    -0.06
    à¸ŀัà¸ģ
    -0.06
    POSITIVE LOGITS
    åĪ°æľĢåIJİ
    0.11
    æľĢé«ĺ
    0.10
    æľĢéķ¿çļĦ
    0.10
    æľĢä½İ
    0.10
    åĴĮæľĢ
    0.09
     ÑģамÑĭм
    0.09
    åľ¨æľĢ
    0.09
     Lowest
    0.09
    æľĢæ·±
    0.09
     lowest
    0.09
    Activations Density 0.293%

    No Known Activations