© 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. 34932
    Prev
    Next
    INDEX
    Explanations

    æŁIJç§įæŁă

    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
    à¸ģาร
    -0.09
    ä¸ŃåĽ½åľ¨
    -0.08
    ä¸Ģ
    -0.08
    less
    -0.08
    线ç¨ĭ
    -0.08
    ä¸Ģ个
    -0.08
    车è¾Ĩåľ¨
    -0.07
    æ°´
    -0.07
    å·¥ä½ľåľ¨
    -0.07
    ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.14
    ä¸įçŁ¥ä¸įè§īä¸Ń
    0.13
    åĮ»çĶŁæĮĩ导ä¸ĭ
    0.13
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.12
    åĮ»çĶŁçļĦæĮĩ导ä¸ĭ
    0.12
    æĦıçļĦ
    0.12
    æľīæķĪæľŁåĨħ
    0.11
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    0.11
    åĵªäºĽæĸ¹éĿ¢
    0.11
    ä¸įç»ıæĦıéĹ´
    0.11
    Activations Density 0.005%

    No Known Activations