© 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. 10985
    Prev
    Next
    INDEX
    Explanations

    increase

    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
    รà¹īาย
    -0.08
    漫éķ¿
    -0.08
    rever
    -0.08
    åħĥ人æ°ijå¸ģ
    -0.07
    eman
    -0.07
    æµĵ度为
    -0.07
    影幽
    -0.07
    ä»»ä½ķéĹ®é¢ĺ
    -0.07
    温度为
    -0.07
    è¿ľä½İäºİ
    -0.07
    POSITIVE LOGITS
    æľīæĽ´å¤ļçļĦ
    0.13
    带æĿ¥æĽ´å¤ļçļĦ
    0.11
    带æĿ¥æĽ´å¤ļ
    0.11
    ìĪĺë¡Ŀ
    0.11
    æĽ´å¤ļçļĦ
    0.11
     اÙĦÙħزÙĬد
    0.10
    æıIJä¾ĽæĽ´å¤ļ
    0.10
    å¢ŀåĬł
    0.10
    æıIJä¾ĽæĽ´å¤ļçļĦ
    0.10
    å¢ŀåĬłçļĦ
    0.09
    Activations Density 0.106%

    No Known Activations