© 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. 19300
    Prev
    Next
    INDEX
    Explanations

    expectation and probability

    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
    arangan
    -0.08
     recl
    -0.08
    ARGV
    -0.08
    indr
    -0.08
    =cut
    -0.07
    åĶ±
    -0.07
    گرÛĮ
    -0.07
    লà§įপ
    -0.07
     Ult
    -0.07
    åĢĴ
    -0.07
    POSITIVE LOGITS
    åĿĩåĢ¼
    0.10
     expectation
    0.08
    .mean
    0.08
    æ¦Ĥçİĩ
    0.07
    prob
    0.07
     Mean
    0.07
     covariance
    0.07
    çĭ¬ç«ĭæĢ§
    0.07
    åı
    0.07
     probabil
    0.07
    Activations Density 0.004%

    No Known Activations