© 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. 43011
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

    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
    edException
    -0.08
    à§ĩà¦ķà§ĩ
    -0.07
    æĺ¯å°Ĩ
    -0.07
    éĩijåŃĹå¡Ķ
    -0.07
    æĺ¯è¢«
    -0.07
    æĺ¯ç¾İåĽ½
    -0.07
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.07
    çĿ¡çĿĢ
    -0.07
    æ°´ä¸ĭ
    -0.07
    款çļĦ
    -0.07
    POSITIVE LOGITS
    ä¼Ł
    0.07
    oyo
    0.07
    P
    0.07
    ä¸Ģçľĭ
    0.07
    ление
    0.07
    带åĪ°äºĨ
    0.07
    ple
    0.07
    pel
    0.06
     unc
    0.06
    eways
    0.06
    Activations Density 0.201%

    No Known Activations