© 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. 2760
    Prev
    Next
    INDEX
    Explanations

    President's army or country's victories

    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
     somewhat
    -0.09
    æĺ¾å¾ĹæľīäºĽ
    -0.08
    éĥ½ä¸į太
    -0.08
    åįijå¾®
    -0.08
    æľªåħį
    -0.07
    ä¸įå°ıçļĦ
    -0.07
    ç¿ł
    -0.07
    úm
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    é¢ĩ为
    -0.07
    POSITIVE LOGITS
    åħļåĴĮ
    0.08
    ä¿ĿéļľäºĨ
    0.08
    æľīä¿¡å¿ĥ
    0.08
    人æ°ijçļĦ
    0.08
    ç»Ŀ对ä¸įä¼ļ
    0.08
    çļĦä¼Łå¤§
    0.08
    æĿ¥ä¹ĭä¸įæĺĵ
    0.07
    åĿļå®ļä¸į移
    0.07
    ç»Ŀä¸įä¼ļ
    0.07
    æĹłæ¯Ķ
    0.07
    Activations Density 0.085%

    No Known Activations