© 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. 38315
    Prev
    Next
    INDEX
    Explanations

    class a or class ab

    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
    kok
    -0.08
    ä½ĨçĶ±äºİ
    -0.08
    äºĨå°±
    -0.08
    åĸĿä¸ĢæĿ¯
    -0.07
    Pending
    -0.07
    çĶ±äºİ
    -0.07
    ç§ijåѦåĮĸ
    -0.07
    ç»Ļä½łä¸Ģ个
    -0.07
    Due
    -0.07
    æĺ¯åIJ¦ä¼ļ
    -0.07
    POSITIVE LOGITS
    èĩ³å°ijåľ¨
    0.10
    å¿ħé¡»æĺ¯
    0.09
    æīįè¡Į
    0.08
     must
    0.08
     likely
    0.08
    å¾Īåı¯èĥ½æĺ¯
    0.08
    å¿ħé¡»
    0.08
    å¿ħé¡»åľ¨
    0.08
    å¿ħå®ļ
    0.08
     Must
    0.08
    Activations Density 0.030%

    No Known Activations