© 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. 60499
    Prev
    Next
    INDEX
    Explanations

    approximation theory

    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
    ä¸įè¾ŀ
    -0.06
    赫çĦ¶
    -0.06
    less
    -0.06
    elmes
    -0.06
    ystal
    -0.06
    æĥħæŃĮ
    -0.06
     ÙĪاØŃد
    -0.06
    íĺij
    -0.06
    为åŃ©åŃIJ们
    -0.06
    omatis
    -0.06
    POSITIVE LOGITS
    éĢ¼è¿ij
    0.10
    getError
    0.09
     approximation
    0.08
    bilt
    0.08
    æ¸IJ
    0.08
    ç¥ŀä¹ĭ
    0.08
    imating
    0.08
    ieza
    0.08
    误差
    0.08
    _approx
    0.08
    Activations Density 0.007%

    No Known Activations