© 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. 16484
    Prev
    Next
    INDEX
    Explanations

    DSL Technology

    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
    Deal
    -0.07
     mixed
    -0.07
     Mixed
    -0.06
    ä¸į为人
    -0.06
    otte
    -0.06
     Deal
    -0.06
    æ··åIJĪ
    -0.06
    bsp
    -0.06
    ä¸Ģå¼ı
    -0.06
    /rs
    -0.06
    POSITIVE LOGITS
    ennem
    0.08
    æĸĩéĿĻ
    0.08
    æģ©
    0.08
    schau
    0.07
    langs
    0.07
    illard
    0.07
    кÑĥда
    0.07
    emuk
    0.07
    unjung
    0.07
    ynchronous
    0.07
    Activations Density 0.002%

    No Known Activations