© 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. 21244
    Prev
    Next
    INDEX
    Explanations

    polynomials and functions

    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
    æĤ£
    -0.09
    沫
    -0.08
    ä¸ŃåĽ½ç«Ļ
    -0.08
    åĿĢ
    -0.08
    缮çļĦçļĦ
    -0.07
    ä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    -0.07
    oloc
    -0.07
    elib
    -0.07
    á»ij
    -0.07
    è¿ŀåIJĮ
    -0.07
    POSITIVE LOGITS
    족
    0.07
     primitives
    0.07
    å¤
    0.06
    å°ĸ
    0.06
     solutions
    0.06
    éĸ¢
    0.06
     derivatives
    0.06
    éŨ类
    0.06
     inverse
    0.06
     generalized
    0.06
    Activations Density 0.008%

    No Known Activations