© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17081
    Prev
    Next
    INDEX
    Explanations

    statistics and statistical methods

    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
     ELECTR
    -0.09
    çªŁ
    -0.08
    Programm
    -0.08
    ãĤ®ãĥª
    -0.07
    è°IJæĮ¯
    -0.07
    å°½æĺ¯
    -0.07
    ragment
    -0.07
     electr
    -0.07
    Ùĩرب
    -0.07
    Injected
    -0.07
    POSITIVE LOGITS
     statist
    0.14
    ç»Łè®¡
    0.13
    ç»Łè®¡åѦ
    0.12
     statistical
    0.12
     statistic
    0.12
    估计
    0.11
     Bayesian
    0.11
     estimator
    0.11
    æĬ½æł·
    0.11
     Statistical
    0.11
    Activations Density 0.311%

    No Known Activations