© 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. 32282
    Prev
    Next
    INDEX
    Explanations

    spherical harmonic polynomials or wave equations

    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
    ameda
    -0.07
    ério
    -0.07
    éķ¿çļĦ
    -0.07
    年头
    -0.07
    æĹłç©·çļĦ
    -0.07
    rese
    -0.06
    æĿ¡
    -0.06
    ÏĦίαÏĤ
    -0.06
    è·ijäºĨ
    -0.06
    /gtest
    -0.06
    POSITIVE LOGITS
    é«ĺçħ§
    0.08
    ropriate
    0.08
    -angular
    0.08
     polar
    0.07
    lieder
    0.07
    .standard
    0.07
     azimuth
    0.07
    inna
    0.07
     appropriate
    0.07
     rotational
    0.07
    Activations Density 0.003%

    No Known Activations