© 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. 33502
    Prev
    Next
    INDEX
    Explanations

    copyright notices and dates

    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
    订éĺħä¸ĵæłı
    -0.09
    æ¯ĴçĹĩ
    -0.08
    aha
    -0.07
    </tool_call>
    -0.07
    è°¢
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
    æľ¬æĸĩ为åįļ主
    -0.07
    æĪij为群ä¼ĹåĬŀå®ŀäºĭ
    -0.07
    æŁ¥çľĭæĽ´å¤ļä¿¡æģ¯
    -0.07
    è··
    -0.07
    POSITIVE LOGITS
     infatti
    0.06
     Gelt
    0.06
     bowiem
    0.06
    äºĴåĬ¨äº¤æµģ
    0.06
    adiens
    0.06
    åijĬçŁ¥ä¹¦
    0.06
    å®
    0.06
     Owen
    0.05
    imli
    0.05
    ç²īçļĦ
    0.05
    Activations Density 1.374%

    No Known Activations