© 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. 65339
    Prev
    Next
    INDEX
    Explanations

    learning process and experience

    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
    AAA
    -0.08
    审
    -0.08
    °
    -0.07
    .NewReader
    -0.07
    atile
    -0.07
    olan
    -0.07
    AAAA
    -0.07
    ypes
    -0.07
    gross
    -0.07
    gada
    -0.07
    POSITIVE LOGITS
    -learning
    0.09
    -disabled
    0.08
    åĴĮå·¥ä½ľ
    0.08
    åĴĮåŃ¦ä¹ł
    0.08
    æĪIJæŀľ
    0.08
    learning
    0.07
    تاب
    0.07
     environments
    0.07
     occured
    0.07
    Ĥ
    0.07
    Activations Density 0.033%

    No Known Activations