© 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. 60602
    Prev
    Next
    INDEX
    Explanations

    programmed settings

    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
    BoundingClientRect
    -0.07
    FIXME
    -0.07
    åĮħè£ħæĿIJæĸĻ
    -0.07
     JDK
    -0.06
    TODO
    -0.06
    窥éķľ
    -0.06
    æ§ĭ
    -0.06
    OMPI
    -0.06
    èĴĤ
    -0.06
     Philipp
    -0.06
    POSITIVE LOGITS
     mode
    0.11
     preset
    0.11
     settings
    0.11
    模å¼ı
    0.10
    模å¼ıä¸ĭ
    0.10
     programmed
    0.10
    mode
    0.09
    设å®ļçļĦ
    0.09
    模å¼ıåĴĮ
    0.09
     modes
    0.09
    Activations Density 0.125%

    No Known Activations