© 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. 47146
    Prev
    Next
    INDEX
    Explanations

    mode options

    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
    igon
    -0.06
    çĨ¬å¤ľ
    -0.06
    olan
    -0.06
    å¯ĮåIJ«
    -0.06
    çĻ¾åĢį
    -0.06
    åįĹèĩ³
    -0.06
     ulaÅŁ
    -0.06
    iol
    -0.06
    è®¤çľŁå±¥è¡Į
    -0.06
     Ser
    -0.06
    POSITIVE LOGITS
    管çIJĨ模å¼ı
    0.11
    模å¼ıä¸ĭ
    0.11
    模å¼ıä¸Ń
    0.10
     rež
    0.10
     ÑĢежим
    0.09
     mode
    0.09
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.09
    -lite
    0.09
     modalidad
    0.09
    æĶ¹ä¸º
    0.09
    Activations Density 0.114%

    No Known Activations