© 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. 60597
    Prev
    Next
    INDEX
    Explanations

    competence and capability

    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
    agens
    -0.09
    leigh
    -0.09
    Õµ
    -0.08
    abouts
    -0.08
    ivals
    -0.08
    .EMPTY
    -0.08
    agged
    -0.07
    æĽ´å¤ļ精彩åĨħ容
    -0.07
    à¹Ħร
    -0.07
    гло
    -0.07
    POSITIVE LOGITS
    fully
    0.09
    åįģ足çļĦ
    0.09
    ä½İä¸ĭ
    0.09
    åĴĮèĥ½åĬĽ
    0.08
    abilities
    0.08
    /power
    0.08
    åĴĮä¹īåĬ¡
    0.08
    è¶Ĭ强
    0.08
    åĩºä¼Ĺ
    0.08
    èĥ½åĬĽçļĦ
    0.07
    Activations Density 0.053%

    No Known Activations