© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25052
    Prev
    Next
    INDEX
    Explanations

    test case or test suite

    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
    å¤ļåĽ¾
    -0.08
    西游
    -0.07
    allah
    -0.07
    ç´Ĭ
    -0.07
     Sinclair
    -0.07
    æĢ¨è¨Ģ
    -0.06
    èµ°ä½İ
    -0.06
    adian
    -0.06
    SE
    -0.06
    aga
    -0.06
    POSITIVE LOGITS
     tests
    0.14
    æµĭè¯ķ
    0.13
     testing
    0.11
    tests
    0.11
     Tests
    0.10
    éªĮè¯ģ
    0.10
     test
    0.10
    測試
    0.09
    éªĮæĶ¶
    0.09
    testing
    0.09
    Activations Density 0.034%

    No Known Activations