© 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. 14323
    Prev
    Next
    INDEX
    Explanations

    following parts, products, or outcomes

    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
    ิà¹Īà¸ĩ
    -0.07
    elson
    -0.07
    andum
    -0.07
    åѦåĪ°äºĨå¾Īå¤ļ
    -0.07
    immer
    -0.06
     Zuk
    -0.06
    eting
    -0.06
    ারà§įথ
    -0.06
    ç¢į
    -0.06
    ITAL
    -0.06
    POSITIVE LOGITS
     namely
    0.09
    åı«åģļ
    0.09
     called
    0.09
    称为
    0.09
    —the
    0.09
    åĪĨåĪ«æĺ¯
    0.08
    ìŀIJìĿ¸
    0.08
    ìĿ¸
    0.08
     olan
    0.08
    åı«ä»Ģä¹Ī
    0.08
    Activations Density 0.120%

    No Known Activations