© 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. 51400
    Prev
    Next
    INDEX
    Explanations

    lists and documents

    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
    åİĮ
    -0.07
     mir
    -0.07
    åĭī强
    -0.07
    çİĭæĢĿ
    -0.06
     rem
    -0.06
     around
    -0.06
    ped
    -0.06
    屿
    -0.06
    irst
    -0.06
    å¹¢
    -0.06
    POSITIVE LOGITS
    aios
    0.08
    ä¸Ĭè¿°
    0.08
    boxed
    0.07
    åį¡è¥¿
    0.07
    å¥ĭæĸĹçļĦ
    0.07
    ç²¾ç¥ŀåĴĮ
    0.07
    åľ¨ä¸Ĭè¿°
    0.07
    inson
    0.07
    krat
    0.07
    æĵĴ
    0.07
    Activations Density 0.002%

    No Known Activations