© 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. 23696
    Prev
    Next
    INDEX
    Explanations

    version numbers and documentation tags

    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
    borg
    -0.09
    ë¸Į리
    -0.08
    ุà¹Īà¸Ļ
    -0.08
    añ
    -0.08
    ofer
    -0.08
    kent
    -0.08
    ientes
    -0.08
    Ã¤ÃŁ
    -0.07
    Ã¤ÃŁig
    -0.07
    CORD
    -0.07
    POSITIVE LOGITS
    ↵
    0.07
    详尽
    0.07
    Ń
    0.06
    æĪĺåĮº
    0.06
     data
    0.06
    åķĨå®ļ
    0.06
    Urls
    0.06
    atat
    0.06
     most
    0.06
    çī¹çĤ¹çļĦ
    0.06
    Activations Density 0.123%

    No Known Activations