© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59975
    Prev
    Next
    INDEX
    Explanations

    curve fitting and optimization

    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
    Negative Logits
     Advisory
    -0.07
    EGI
    -0.06
    æīĵäºĨ个
    -0.06
     Asli
    -0.06
    stufe
    -0.06
     natur
    -0.06
     advis
    -0.06
    _queries
    -0.06
     Zas
    -0.06
    ứng
    -0.06
    POSITIVE LOGITS
     fitting
    0.12
    æĭŁåIJĪ
    0.12
    fit
    0.11
     fittings
    0.10
    -fit
    0.10
    Fit
    0.10
     parameters
    0.10
     Parameters
    0.10
     fit
    0.09
    .fit
    0.09
    Activations Density 0.069%

    No Known Activations