© 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. 45965
    Prev
    Next
    INDEX
    Explanations

    text separators and symbols

    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
    çļĭ
    -0.08
    ä¹Łæĺ¯
    -0.07
    /unit
    -0.07
    ë²łìĿ´
    -0.07
    @$
    -0.06
    éļıåľ°
    -0.06
    ä¸įä½Ĩ
    -0.06
     appunto
    -0.06
    ä¹Łæĺ¯éĿŀ常
    -0.06
    å¹ħ
    -0.06
    POSITIVE LOGITS
    æĸ¹å¼ı使çĶ¨
    0.09
    èĭijå°ıåĮº
    0.07
    kek
    0.07
     Æ¡i
    0.07
    еÑĤен
    0.07
    çĶµè¯ĿèģĶç³»
    0.07
    ÄĥÈĻ
    0.07
    èĮĥåĽ´åĨħ使çĶ¨
    0.07
    第ä¸Ģè½®
    0.07
     alde
    0.07
    Activations Density 0.015%

    No Known Activations