© 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. 16142
    Prev
    Next
    INDEX
    Explanations

    phenomenon or arising from

    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
    ç§Ģ丽
    -0.08
    ä¸¥æł¼è¦ģæ±Ĥ
    -0.07
    ä¸įåı¯ä»¥
    -0.07
    åŁºæľ¬è¦ģæ±Ĥ
    -0.07
    gmt
    -0.07
    egrity
    -0.07
    issen
    -0.07
    æľĢéĩįè¦ģçļĦ
    -0.07
    æĮīçħ§è§Ħå®ļ
    -0.07
    ç«ŀåĵģä¿¡æģ¯
    -0.07
    POSITIVE LOGITS
    è¿Ļç§įçݰ象
    0.13
    çŃīçݰ象
    0.10
    çݰ象
    0.10
     phenomenon
    0.10
     unintended
    0.10
    çļĦçݰ象
    0.09
    çı¾è±¡
    0.09
    ä¹ħèĢĮä¹ħä¹ĭ
    0.09
     patterns
    0.09
     phenomena
    0.09
    Activations Density 0.067%

    No Known Activations