© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15680
    Prev
    Next
    INDEX
    Explanations

    cache service / aws sync / time breaks

    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
    ollapsed
    -0.08
    oga
    -0.07
    {text
    -0.07
    utex
    -0.07
    ango
    -0.07
    çļĦå°ıç¼ĸ
    -0.06
    ker
    -0.06
    åĪĨå±Ģ
    -0.06
    oling
    -0.06
    æĺĮå¹³
    -0.06
    POSITIVE LOGITS
    对ä¸Ĭè¿°
    0.10
    ä¸Ĭè¿°
    0.10
    åľ¨ä¸Ĭè¿°
    0.10
    ä¸Ĭè¨ĺ
    0.08
     aforementioned
    0.08
    ((((
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.07
    åIJĮä¸Ĭ
    0.07
     above
    0.07
    uah
    0.07
    Activations Density 0.033%

    No Known Activations