© 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. 58440
    Prev
    Next
    INDEX
    Explanations

    class of categories

    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
    egram
    -0.06
    port
    -0.06
    idik
    -0.06
    驱
    -0.06
     prover
    -0.06
    ä¸Ģæĸĩ
    -0.06
    æĦī
    -0.06
     khẩn
    -0.06
    åĨįæĿ¥
    -0.06
    ä¸ĢåŃĹ
    -0.06
    POSITIVE LOGITS
    æĹłèĻij
    0.08
    жеÑģÑĤво
    0.08
     subset
    0.08
    éĹ¨æ§Ľ
    0.08
    mongo
    0.08
    Filtered
    0.08
    该类
    0.08
    ières
    0.08
     Ùģئة
    0.08
    ç»ıçIJĨ人
    0.08
    Activations Density 0.039%

    No Known Activations