© 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. 21988
    Prev
    Next
    INDEX
    Explanations

    def, des, den, hyper

    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
    ä¸įåłª
    -0.08
    翼翼
    -0.08
    ä¾ĽåºĶéĩı
    -0.07
    illons
    -0.07
    oid
    -0.07
    oplevel
    -0.07
    ä¹ĭ家
    -0.07
    holder
    -0.07
    æĮģæľī人
    -0.07
    eldo
    -0.06
    POSITIVE LOGITS
    æľĪ以æĿ¥
    0.09
    åIJĪåIJĮæŶ
    0.08
    /rem
    0.07
    æ°´åĴĮ
    0.07
    çļĦä¸įæĺ¯
    0.07
    åĴĮåĪ©çĶ¨
    0.07
    าศ
    0.07
    åĴĮ使çĶ¨
    0.07
    /display
    0.07
    /edit
    0.07
    Activations Density 0.045%

    No Known Activations