© 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. 29648
    Prev
    Next
    INDEX
    Explanations

    location or origin descriptors

    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
    jsc
    -0.07
    ebr
    -0.07
    roj
    -0.07
    desc
    -0.07
    æĸ°æŧ
    -0.06
    å¨Ĩ
    -0.06
     Baru
    -0.06
    çķĻç»Ļ
    -0.06
    æѦç¥ŀ
    -0.06
    æľªæĽ¾
    -0.06
    POSITIVE LOGITS
    ìŀIJìĿ¸
    0.15
    ä¹Łå°±æĺ¯
    0.14
     yaitu
    0.14
    åį³ä»¥
    0.13
     namely
    0.12
    åį³
    0.12
    —which
    0.11
    åį³åľ¨
    0.11
     ÛĮعÙĨÛĮ
    0.11
    yait
    0.11
    Activations Density 0.241%

    No Known Activations