© 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. 12542
    Prev
    Next
    INDEX
    Explanations

    Fifth District of Texas

    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
    ä½IJ
    -0.09
    å¼ķ
    -0.07
     nesting
    -0.06
    rvine
    -0.06
    Nested
    -0.06
    hr
    -0.06
    ↵
    -0.06
    serial
    -0.06
    regexp
    -0.06
     guided
    -0.06
    POSITIVE LOGITS
    éĶĻ误æĪĸ
    0.08
    lada
    0.07
    æĮĿ
    0.07
    ä¹ĭåĪĹ
    0.07
    _again
    0.07
    æ½¢
    0.07
    isian
    0.07
    faz
    0.07
    æĽ¿ä½ł
    0.07
    æĮ¥èĪŀ
    0.07
    Activations Density 0.063%

    No Known Activations