© 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. 9016
    Prev
    Next
    INDEX
    Explanations

    `id` or `card` following `(`

    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
     Cousins
    -0.07
    ä¼¯æł¼
    -0.07
    íĤ¹
    -0.07
    ogos
    -0.07
    orda
    -0.07
    ÙĨع
    -0.07
    çļĦå¦Īå¦Ī
    -0.07
    åĩ«
    -0.07
     pouc
    -0.07
    PrototypeOf
    -0.07
    POSITIVE LOGITS
    AccessType
    0.08
    ä¸Ĭæŀ¶
    0.07
    è±Į
    0.07
     truff
    0.06
    éķľ
    0.06
     ÐĹаÑĤо
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    æĬ¢çľ¼
    0.06
    ä¸īä½ĵ
    0.06
    æĵĬ
    0.06
    Activations Density 0.001%

    No Known Activations