© 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. 17659
    Prev
    Next
    INDEX
    Explanations

    should be

    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
    stin
    -0.09
    xaa
    -0.09
     пÑĢедÑģÑĤоиÑĤ
    -0.08
    kini
    -0.08
    ĵ¨
    -0.08
    ÑĪка
    -0.08
    awei
    -0.08
    xbf
    -0.08
    seh
    -0.08
    oids
    -0.08
    POSITIVE LOGITS
    ä¸įåºĶ该
    0.13
     ideally
    0.11
     be
    0.11
    ä¹ŁåºĶ该
    0.09
    ä¸į该
    0.09
     should
    0.09
    ered
    0.09
    ä¹ŁåºĶ
    0.08
    ering
    0.08
    ä¸įåºĶ
    0.08
    Activations Density 0.186%

    No Known Activations