© 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. 60667
    Prev
    Next
    INDEX
    Explanations

    division or fraction parsing

    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
    ves
    -0.09
    çĤ¹å¯¹
    -0.07
    è¿ĺæľīä¸įå°ij
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    ugen
    -0.07
    æłĩé«ĺ
    -0.07
    ê»
    -0.07
    ugd
    -0.07
    oron
    -0.07
    atically
    -0.07
    POSITIVE LOGITS
    occhi
    0.07
    ella
    0.07
     readdir
    0.07
    ellas
    0.07
    ÙĦاء
    0.07
    iglia
    0.06
    ashi
    0.06
    hill
    0.06
    票
    0.06
    OfFile
    0.06
    Activations Density 0.014%

    No Known Activations