© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16357
    Prev
    Next
    INDEX
    Explanations

    French/Spanish/Japanese/Russian grammar

    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
     "
    -0.07
    ä¸ŃåŃĺåľ¨
    -0.06
    åĭī
    -0.06
    åѦçĶŁä»£è¡¨
    -0.06
    (static
    -0.05
    西åİ¿
    -0.05
     Representative
    -0.05
    åIJį为
    -0.05
     p
    -0.05
     Scrolls
    -0.05
    POSITIVE LOGITS
    ä¸Ģè¯į
    0.10
    è¿Ļ个è¯į
    0.09
    äºĮåŃĹ
    0.09
     seguida
    0.08
    epam
    0.08
    ///<
    0.08
    éĢĤçĶ¨çļĦ
    0.08
    ãģ¨ãģĦãģĨè¨Ģèijī
    0.08
    æĺ¯ä¸Ģ个å¾Ī
    0.08
    æľ¬èº«
    0.07
    Activations Density 0.006%

    No Known Activations