© 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. 16160
    Prev
    Next
    INDEX
    Explanations

    grammatical terms and abbreviations

    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
    ajer
    -0.08
    каде
    -0.08
    èĤļçļ®
    -0.07
    лма
    -0.07
    gül
    -0.07
    ennes
    -0.07
    å¹¿æ³Ľå®£ä¼ł
    -0.07
    chado
    -0.07
     Zoll
    -0.07
    uarios
    -0.07
    POSITIVE LOGITS
    ä»İåı¥
    0.08
    åīįç½®
    0.08
    修饰
    0.08
    enant
    0.07
    åIJijæĹ¥
    0.07
    åIJİç½®
    0.07
    éļľ
    0.07
    ourd
    0.07
    è¿ĩéķ¿
    0.06
    Âł
    0.06
    Activations Density 0.004%

    No Known Activations