© 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. 19603
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ÙĨج
    -0.08
    ëĭ¤ê°Ģ
    -0.07
    ervi
    -0.07
    quil
    -0.07
    oteca
    -0.07
    çļĦè¯Ħä»·æĺ¯
    -0.06
    çļĦ主人
    -0.06
    æľ¬èģĮ
    -0.06
    orma
    -0.06
    uploader
    -0.06
    POSITIVE LOGITS
    jee
    0.07
    åĢį
    0.07
    izi
    0.07
    æ¯Ĺ
    0.07
    eldom
    0.07
    gregate
    0.07
    æĶ¶èĹıæľ¬ç«Ļ
    0.06
     تÙĦا
    0.06
    åľ¨åIJĮä¸Ģ
    0.06
    ç«Ńè¯ļ
    0.06
    Activations Density 0.001%

    No Known Activations