© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 63900
    Prev
    Next
    INDEX
    Explanations

    . therefore

    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
     totiž
    -0.09
    åIJ¦åĪĻä¼ļ
    -0.08
    ç±į
    -0.07
    olg
    -0.07
    èĢĮæĺ¯è¦ģ
    -0.06
    æĸ¹éĩĿ
    -0.06
    ç«ĭè¶³
    -0.06
    缴æİ¥åħ³ç³»åΰ
    -0.06
    ลà¸ĩà¹Ħà¸Ľ
    -0.06
    ä¸įçķ¶
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įçݰ象
    0.11
    严éĩįæĹ¶
    0.10
    erschein
    0.09
    è¿Ļ个è¿ĩç¨ĭ
    0.09
    èĤīçľ¼
    0.08
    被称为
    0.08
    å¾Ĺä¸įåģ¿
    0.08
     phenomenon
    0.08
    è¿Ļ便æĺ¯
    0.08
    çŃīçݰ象
    0.08
    Activations Density 0.107%

    No Known Activations