© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30242
    Prev
    Next
    INDEX
    Explanations

    e-commerce, digital, telehealth

    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
    åĸĦèī¯çļĦ
    -0.08
    ç»ıèIJ¥é¡¹çĽ®
    -0.06
    داÙĨ
    -0.06
     infine
    -0.06
    {{$
    -0.06
    itemap
    -0.06
    ç»ıåķĨ
    -0.06
    éĹªèĢĢ
    -0.06
     sadd
    -0.06
    rippling
    -0.06
    POSITIVE LOGITS
     digital
    0.10
    ä¸İä¼łç»Ł
    0.10
    缺å¸Ń
    0.09
    Digital
    0.09
    èĻļæĭŁ
    0.09
    足ä¸įåĩºæĪ·
    0.09
     convenience
    0.08
     ë³´ìĻĦ
    0.08
    便åĪ©æĢ§
    0.08
    è¿ľç¨ĭ
    0.08
    Activations Density 0.136%

    No Known Activations