© 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. 28980
    Prev
    Next
    INDEX
    Explanations

    bombing during the century

    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
    è·¯åĮĹ
    -0.08
    è¡Įç¨ĭå®īæİĴ
    -0.07
    åIJ´æ±Ł
    -0.07
    udir
    -0.07
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    -0.07
    æľĪ份å¼Ģå§ĭ
    -0.07
    ç½ijæł¡
    -0.07
    è¸ıè¸ıå®ŀ
    -0.07
    abus
    -0.07
    èĩªåݻ年
    -0.07
    POSITIVE LOGITS
     modern
    0.12
    çݰ代çļĦ
    0.10
    çݰ代
    0.10
    çݰ代人
    0.10
    æĺ¯çݰ代
    0.10
    çļĦçݰ代
    0.10
    modern
    0.09
    è¿ijçݰ代
    0.09
     moderne
    0.09
     Modern
    0.09
    Activations Density 0.373%

    No Known Activations