© 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. 56817
    Prev
    Next
    INDEX
    Explanations

    circumference: objects

    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
    è¿Ŀåıįä¸Ĭè¿°
    -0.08
    odio
    -0.07
    raphic
    -0.07
     رÙĪÙĨ
    -0.07
    anggal
    -0.07
     republ
    -0.07
    orest
    -0.07
    raÄį
    -0.07
    äºijå±±
    -0.07
    _MAXIMUM
    -0.07
    POSITIVE LOGITS
    çī©ä½ĵ
    0.08
    çī©ä½ĵçļĦ
    0.08
    æľ¬é¢Ĩ
    0.07
    çݰ象
    0.07
    åľ¨çĶŁæ´»ä¸Ń
    0.07
    壶
    0.07
    rese
    0.07
    å¢ŀ大
    0.07
    çļĦç§ijåѦ
    0.07
    åģļåĬŁ
    0.06
    Activations Density 0.001%

    No Known Activations