© 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. 23101
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

    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
    æıIJä¾ĽæĽ´å¤ļ
    -0.07
    สุà¸Ķà¸Ĺà¹īาย
    -0.07
    ä¼¼ä¹İä¹Ł
    -0.07
     Ultimately
    -0.07
    rang
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    аÑĤÑĥÑĢ
    -0.07
    éļ¾æĢª
    -0.06
    are
    -0.06
    gun
    -0.06
    POSITIVE LOGITS
     oppure
    0.08
    ergen
    0.07
    ä¹Łç§°ä¸º
    0.07
    ogl
    0.07
    aran
    0.06
    oret
    0.06
    bout
    0.06
     Vertr
    0.06
    oms
    0.06
    ç½ij讯
    0.06
    Activations Density 0.053%

    No Known Activations