© 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. 9839
    Prev
    Next
    INDEX
    Explanations

    java.util programming constructs

    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
    åĴĮ
    -0.23
    ë¡ľ
    -0.15
    ãĤĴ
    -0.14
    à¸Ĺีà¹Ī
    -0.14
    ìĻĢ
    -0.13
    åĴĮåIJĮåѦ
    -0.12
    åĴĮæľīåħ³
    -0.12
    åĴĮåįķä½į
    -0.12
    ой
    -0.11
    åĴĮçĪ¶æ¯į
    -0.11
    POSITIVE LOGITS
    ÛĮ
    0.10
    ary
    0.09
    nya
    0.09
    çļĦ
    0.08
    à¹Ĩ
    0.08
    ано
    0.08
    èIJ©
    0.07
    ãģĵãĤĮãĤĤ
    0.07
    য়ার
    0.07
    åĬłæĭ¿å¤§
    0.07
    Activations Density 0.455%

    No Known Activations