© 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. 22356
    Prev
    Next
    INDEX
    Explanations

    referring to copyright or abstract

    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
    ami
    -0.08
    crement
    -0.07
    éŨä¸ĭ
    -0.07
    uti
    -0.07
    uster
    -0.07
    iere
    -0.07
    gens
    -0.07
    æĸĩç«łæĿ¥æºIJ
    -0.07
    ught
    -0.07
    è¯Ŀ说
    -0.07
    POSITIVE LOGITS
    Ø¢Ùħ
    0.07
     lan
    0.07
    ä¿Ŀå§Ĩ
    0.07
    åĩ
    0.06
    etzen
    0.06
    ehrte
    0.06
    cntl
    0.06
    کارÛĮ
    0.06
    åĺī
    0.06
    ä½łæīĢ
    0.06
    Activations Density 0.001%

    No Known Activations