© 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. 686
    Prev
    Next
    INDEX
    Explanations

    assessments and grading criteria

    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
    Negative Logits
    çŃ
    -0.07
    åĻ
    -0.07
    ä¸İåĽ½åĨħ
    -0.06
     bong
    -0.06
    èݽ
    -0.06
    ç»Ŀå¢ĥ
    -0.06
    è°ĥåĴĮ
    -0.06
     Barton
    -0.06
    headline
    -0.06
    åŁºç¡ĢçłĶ究
    -0.06
    POSITIVE LOGITS
    è¯Ħå®ļ
    0.14
    è¯Ħä»·
    0.13
    è¯Ħ
    0.13
    è©ķ
    0.13
     evalu
    0.12
     evaluation
    0.12
    æīĵåĪĨ
    0.12
    çļĦè¯Ħä»·
    0.12
    è¯ĦåĪĨ
    0.12
     evaluations
    0.12
    Activations Density 0.055%

    No Known Activations