© 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. 64834
    Prev
    Next
    INDEX
    Explanations

    code, function calls, and generics

    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
    izen
    -0.07
    dog
    -0.07
    drv
    -0.07
    isée
    -0.07
    kea
    -0.07
    cplusplus
    -0.07
    åłĢ
    -0.07
    è·Łåľ¨
    -0.06
    åı¯å¯¹
    -0.06
    .im
    -0.06
    POSITIVE LOGITS
    Ùĩاب
    0.07
    angg
    0.07
    æĺİçĻ½
    0.06
    "But
    0.06
    енеÑĢа
    0.06
    Ñģполни
    0.06
    unts
    0.06
    éĢłåĮĸ
    0.06
    нÑĮÑĪе
    0.06
    å°ĨæīĢæľī
    0.06
    Activations Density 0.029%

    No Known Activations