© 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. 26686
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with superscripts and subscripts

    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
    迪奥
    -0.08
    iani
    -0.08
     adher
    -0.06
     '%'
    -0.06
    enburg
    -0.06
    rib
    -0.06
     '|'
    -0.06
    éĺĸ
    -0.06
    (/[
    -0.06
    ä¸īé«ĺ
    -0.06
    POSITIVE LOGITS
    vore
    0.08
     Kli
    0.08
    人大
    0.08
    vero
    0.07
    ีà¸Ļ
    0.07
     Nol
    0.07
    urent
    0.07
    дÑĢÑĥ
    0.07
    ropol
    0.07
    vara
    0.07
    Activations Density 0.033%

    No Known Activations