© 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. 40285
    Prev
    Next
    INDEX
    Explanations

    xml version

    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
    ember
    -0.08
    antai
    -0.07
    ãģľ
    -0.07
    éĿ¢ç²ī
    -0.07
    ÐķÐļ
    -0.07
    indir
    -0.07
    èľĹçīĽ
    -0.07
    ãĥĮ
    -0.07
    ethereum
    -0.07
    दरà¥į
    -0.07
    POSITIVE LOGITS
    /xml
    0.15
    .Xml
    0.14
    /XML
    0.13
    (xml
    0.12
     XML
    0.12
    _xml
    0.12
    (XML
    0.12
     xml
    0.12
    xml
    0.11
    XML
    0.10
    Activations Density 0.366%

    No Known Activations