© 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. 15677
    Prev
    Next
    INDEX
    Explanations

    Woodlands, Scripps, Co-op, Caravel, Dal, University, Ridge, Evil

    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
    ergestellt
    -0.10
    uellement
    -0.09
    galement
    -0.07
    嬢
    -0.07
    ariamente
    -0.07
    äºĨäºĭ
    -0.07
    ÙĮÙij
    -0.07
    almente
    -0.07
    ualmente
    -0.07
    ooks
    -0.07
    POSITIVE LOGITS
    cito
    0.08
    ä»ĭçŁ³
    0.07
    धà¥įय
    0.07
    æĶ¾çŁ¢
    0.06
    onaut
    0.06
    δήÏĢοÏĦε
    0.06
    पà¥įत
    0.06
    çĽ¸ä¼¼æĸĩçĮ®
    0.06
    elah
    0.06
     khứ
    0.06
    Activations Density 0.652%

    No Known Activations