© 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. 64979
    Prev
    Next
    INDEX
    Explanations

    mathematical exponents 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
    à¸Ńà¸ļ
    -0.06
    æĶĢæ¯Ķ
    -0.06
     deme
    -0.06
    åľ¨åĬŀçIJĨ
    -0.06
    unts
    -0.06
     tros
    -0.06
    voire
    -0.06
    åı¤éķĩ
    -0.06
    Ľ
    -0.06
    æ¡Ĩ
    -0.06
    POSITIVE LOGITS
    èĺĭ
    0.08
    æĥħæĦ¿
    0.08
    EmailAddress
    0.07
    ingo
    0.07
    éģ©
    0.07
    RID
    0.07
    éħ¬
    0.07
    avior
    0.07
    INET
    0.07
    á»ĥm
    0.07
    Activations Density 0.002%

    No Known Activations