© 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. 45056
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with integral/summation notation

    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
    ÏĢη
    -0.07
     Cib
    -0.07
    请æĶ¾å¿ĥ
    -0.06
    à¹Ģหล
    -0.06
    menti
    -0.06
    stelle
    -0.06
    广大åħļåijĺ
    -0.06
    arov
    -0.06
    chini
    -0.06
    ç»Ķ
    -0.06
    POSITIVE LOGITS
    rou
    0.08
    åľ¨åĨħçļĦ
    0.07
     Bout
    0.07
    illen
    0.07
    第ä¸īèĢħ
    0.07
    adays
    0.06
     Howell
    0.06
    imb
    0.06
     Becker
    0.06
     else
    0.06
    Activations Density 0.002%

    No Known Activations