© 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. 12749
    Prev
    Next
    INDEX
    Explanations

    development of

    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
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    -0.07
     kese
    -0.07
    å¥½å¥½åľ°
    -0.06
    Å¡tÄĽ
    -0.06
    epar
    -0.06
    ware
    -0.06
    øv
    -0.06
    æľīä¸Ģçķª
    -0.06
    ç³»ç»Łæĺ¯
    -0.06
    åĨħå®¹è¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    æĦĪåıij
    0.10
    人们对
    0.10
    大家对
    0.09
     ÙĪزÙĬادة
    0.09
    æ°´å¹³çļĦæıIJé«ĺ
    0.09
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.09
    =require
    0.09
    èĢĮæĿ¥çļĦ
    0.08
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ人
    0.08
     اÙĦÙħزÙĬد
    0.08
    Activations Density 0.174%

    No Known Activations