© 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. 30215
    Prev
    Next
    INDEX
    Explanations

    influence and inspiration

    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
    幸ç¦ıç¾İ满
    -0.08
    æĮīçħ§åĽ½å®¶
    -0.08
    åĴĮæĶ¹åĸĦ
    -0.07
    telen
    -0.07
    Narrated
    -0.07
    ikel
    -0.06
    欺
    -0.06
    çļĦçī¹
    -0.06
    ائÙĬØ©
    -0.06
    失
    -0.06
    POSITIVE LOGITS
    åIJ¯åıij
    0.11
    æ½ľç§»é»ĺ
    0.11
     inspiration
    0.10
    æ¸ĬæºIJ
    0.08
     influence
    0.08
    æ½ľç§»é»ĺåĮĸ
    0.08
    ãĤĴåıĹãģijãģŁ
    0.08
    åIJ¯è¿ª
    0.08
     influences
    0.08
    ä½ĵçİ°åľ¨
    0.08
    Activations Density 0.061%

    No Known Activations