© 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. 27779
    Prev
    Next
    INDEX
    Explanations

    hot spots

    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
    æĻ¤
    -0.08
    çļĦéĩįè¦ģ举æݪ
    -0.08
    ä¸¤åľ°
    -0.07
    åIJĮéģĵ
    -0.07
    åı¯åĸľ
    -0.07
    кома
    -0.07
    à·Ķà·Ģ
    -0.07
    .cg
    -0.07
    _backend
    -0.07
    æīĢè½½
    -0.07
    POSITIVE LOGITS
     statut
    0.08
    åѤç«ĭ
    0.08
    ä½įç½®ä¸Ĭ
    0.08
    ä½įç½®çļĦ
    0.07
     lonely
    0.07
    ä¸įåıĤä¸İ
    0.07
    ä¸įåıĤåĬł
    0.07
    èĥ½æĪIJ为
    0.07
    åľ°ä½įçļĦ
    0.07
    身ä¸Ĭ
    0.07
    Activations Density 0.019%

    No Known Activations