© 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. 8037
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    æľīä½Ļ
    -0.08
    urr
    -0.07
    olon
    -0.07
    æµij
    -0.07
    æĬ¥éħ¬
    -0.06
    adre
    -0.06
    åıĬæŶåıįé¦Ī
    -0.06
    注åĨĮèµĦæľ¬ä¸º
    -0.06
     necessary
    -0.06
    å°įäºĨ
    -0.06
    POSITIVE LOGITS
    ×¢×Ļ
    0.08
    ppers
    0.07
     contributions
    0.07
    åIJĦå¼ıåIJĦ
    0.07
    dives
    0.07
    zinho
    0.07
    Ñīики
    0.07
    hev
    0.07
    DTV
    0.07
    æĸŃç»Ń
    0.07
    Activations Density 0.001%

    No Known Activations