© 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. 16824
    Prev
    Next
    INDEX
    Explanations

    ORDER command

    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
    ikov
    -0.07
    itier
    -0.07
    åĿŀ
    -0.07
    ä¿IJ
    -0.06
    æĿ¥ä¹ĭ
    -0.06
    upe
    -0.06
    ä¹ĭæīĢ以
    -0.06
    æ¢Ĩ
    -0.06
    该éķĩ
    -0.06
    çļĦç²¾
    -0.06
    POSITIVE LOGITS
     trivial
    0.08
    ç©Ĩæĸ¯
    0.07
    æĹłä»İ
    0.07
    __[
    0.07
    asp
    0.07
    é¢Ĩ导å°ıç»ĦåĬŀåħ¬å®¤
    0.07
    å°±ä¸įçĶ¨
    0.07
    æĹłé¡»
    0.07
    æ¯ĭ庸
    0.07
    è¿ĻæŶ
    0.07
    Activations Density 0.006%

    No Known Activations