© 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. 29208
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific notation

    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
    éķ°
    -0.07
    å°ıåѦè¯Ńæĸĩ
    -0.07
    /tool
    -0.07
    åIJIJ
    -0.07
    ä½İ年级
    -0.06
    dev
    -0.06
     неблаго
    -0.06
    天边
    -0.06
    å¨ģ士å¿Į
    -0.06
    èŀºæĹĭ
    -0.06
    POSITIVE LOGITS
    æ¯Ķä¾ĭ为
    0.10
    æ¯Ķä¾ĭçļĦ
    0.09
    æ¯Ķä¾ĭ
    0.09
     proportions
    0.09
    é¢
    0.09
     ellipse
    0.08
    æ¤ŃåľĨ
    0.08
    æ¤Ń
    0.08
     ellipt
    0.08
     hoops
    0.08
    Activations Density 0.004%

    No Known Activations