© 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. 47140
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    mojom
    -0.07
    grave
    -0.07
     ÐĿедоÑģÑĤа
    -0.07
    åŁĶ寨
    -0.07
    ç«£
    -0.07
    اء
    -0.07
    åĮ»åѦè§Ĥå¯Ł
    -0.07
    ستاÙĨ
    -0.07
    ":["
    -0.07
    å«Į
    -0.07
    POSITIVE LOGITS
    utile
    0.08
    öö
    0.07
    unnan
    0.07
    æݢ寻
    0.07
    urger
    0.07
    дÑĭн
    0.06
    liable
    0.06
    ical
    0.06
    aix
    0.06
    ãģ¨ãĤĤãģ«
    0.06
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.