© 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. 49182
    Prev
    Next
    INDEX
    Explanations

    millions of people annually

    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
    åĻ©
    -0.08
    çĥŃéŨæĸĩç«ł
    -0.07
    æİĴçļĦ
    -0.06
    æĿ¥å¾Ĺ
    -0.06
    æĢ»æĺ¯
    -0.06
    ffee
    -0.06
    æľīä¸Ģçķª
    -0.06
    并æĬ¥
    -0.06
    è¶Ĭéķ¿
    -0.06
    jours
    -0.06
    POSITIVE LOGITS
     annually
    0.10
    ä¹ĭå¤ļ
    0.10
     yearly
    0.09
     ежегодно
    0.09
    atts
    0.09
    æķ°çĻ¾ä¸ĩ
    0.09
    /year
    0.09
     annual
    0.09
     worldwide
    0.09
     millions
    0.09
    Activations Density 0.486%

    No Known Activations