© 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. 2365
    Prev
    Next
    INDEX
    Explanations

    C++ iostream code

    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
    ä¾Ŀ
    -0.08
    -preview
    -0.07
    _preview
    -0.06
    ayani
    -0.06
     bulk
    -0.06
    ¨
    -0.06
    ROUGH
    -0.06
    olver
    -0.06
    bare
    -0.06
    æļ´é¥®
    -0.06
    POSITIVE LOGITS
    ards
    0.07
    version
    0.07
    åľĪåŃIJ
    0.07
     surve
    0.07
    çİ
    0.07
    สร
    0.07
    ypass
    0.07
    okka
    0.07
    ัà¸ļสà¸Ļ
    0.07
    æĺ
    0.07
    Activations Density 0.004%

    No Known Activations