© 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. 48650
    Prev
    Next
    INDEX
    Explanations

    email sign-offs or names

    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
    ev
    -0.07
    ege
    -0.07
    奢ä¾Ī
    -0.07
    èº
    -0.07
    ÑĢег
    -0.07
    ä¸įåıª
    -0.06
    _ARCH
    -0.06
     ifndef
    -0.06
    ç¥ŀçİĭ
    -0.06
    éci
    -0.06
    POSITIVE LOGITS
    apura
    0.08
    bbing
    0.08
    amet
    0.07
     Hue
    0.07
    orce
    0.07
     quals
    0.07
    pics
    0.07
    aq
    0.07
    ÏĨÏīν
    0.07
    amed
    0.07
    Activations Density 0.001%

    No Known Activations