© 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. 39548
    Prev
    Next
    INDEX
    Explanations

    academic and technical topics

    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
    åŁ¼
    -0.07
    åİŁæľ¬
    -0.06
    oples
    -0.06
    heb
    -0.06
    Viol
    -0.06
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    arcy
    -0.06
     Fau
    -0.06
    á»iji
    -0.06
    zett
    -0.06
    POSITIVE LOGITS
     \"
    0.08
    æĻ©
    0.07
    ondas
    0.07
    /latest
    0.07
    insta
    0.07
    læg
    0.07
    çļĦä»Ĭ天
    0.06
    Č↵
    0.06
    iest
    0.06
    ä¹ĭ约
    0.06
    Activations Density 0.247%

    No Known Activations