© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42264
    Prev
    Next
    INDEX
    Explanations

    currency, time zones, specific abbreviations

    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
    ç·£
    -0.07
     mixed
    -0.07
    Ø·ÙĤ
    -0.07
    atto
    -0.07
     zust
    -0.07
     Mixed
    -0.07
    å¼Ľ
    -0.07
    ç¼ĺ
    -0.06
    .pkg
    -0.06
    mixed
    -0.06
    POSITIVE LOGITS
    Åijd
    0.08
    ÑĪенко
    0.08
    à¸ľà¸¹à¹īมี
    0.08
    licit
    0.07
    tra
    0.07
    lius
    0.07
    aseline
    0.07
    ãĥ¼ãĤ¯
    0.07
    ä¸īéĩĮ
    0.07
    arcer
    0.07
    Activations Density 0.038%

    No Known Activations