© 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. 64149
    Prev
    Next
    INDEX
    Explanations

    state legal citations

    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
    rosse
    -0.08
    =-=-=-=-
    -0.08
    {@
    -0.08
    ä¸ĭåIJĮ
    -0.07
    odelist
    -0.07
    جا
    -0.07
    valuator
    -0.07
    венÑĮ
    -0.07
    egis
    -0.07
    ushing
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤ļ
    0.08
     полови
    0.07
    åĿij
    0.07
    panse
    0.07
     ÙħئÙĪÙĬØ©
    0.07
    åĴĮ第
    0.06
    麹
    0.06
    etat
    0.06
    è¿Ļ个æķ°åŃĹ
    0.06
    chs
    0.06
    Activations Density 0.337%

    No Known Activations