© 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. 15659
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and symbols

    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
    æļ¢
    -0.09
    hors
    -0.08
    è¡¥åĬ©éĩij
    -0.08
     Niest
    -0.07
    оÑĤвеÑĤ
    -0.07
    好å¿ĥæĥħ
    -0.07
    edd
    -0.07
    ÙħÙĦت
    -0.07
    PLIED
    -0.07
    QÄIJ
    -0.07
    POSITIVE LOGITS
    å½Ĵ
    0.06
    acz
    0.06
    士
    0.06
    çŀ°
    0.06
    gefü
    0.06
    åĸľäºĭ
    0.06
    å½ĴæĿ¥
    0.06
    èIJ¦
    0.06
    çļĭ
    0.06
    èIJ¥ä¸ļåijĺ
    0.05
    Activations Density 0.175%

    No Known Activations