© 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. 30964
    Prev
    Next
    INDEX
    Explanations

    format types

    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
    溢
    -0.08
    ç«ĻåĪ°
    -0.07
    à¸Ĭา
    -0.07
    éĢļè¿ĩåIJİ
    -0.06
    温
    -0.06
     Hat
    -0.06
    饿
    -0.06
     sidel
    -0.06
     stage
    -0.06
    ivio
    -0.06
    POSITIVE LOGITS
    æĸĩä»¶æł¼å¼ı
    0.09
    FORMAT
    0.08
    æĬī
    0.08
    IFORM
    0.07
    Unicode
    0.07
    -format
    0.07
    formats
    0.07
    å¤įå¼ı
    0.07
     formatos
    0.07
    atypes
    0.07
    Activations Density 1.346%

    No Known Activations