© 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. 52009
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms

    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
    ãĥ¼ãĤ¸
    -0.08
    é«ĺ级模å¼ı
    -0.08
    bili
    -0.07
    ×ķף
    -0.07
    ontan
    -0.07
     prostituerade
    -0.07
    listed
    -0.07
    agio
    -0.07
    ILLED
    -0.07
    ковано
    -0.07
    POSITIVE LOGITS
    çļĦè¿IJçĶ¨
    0.10
    æ´»åĬ¨çļĦå¼Ģå±ķ
    0.08
    åĪ¶åº¦å»ºè®¾
    0.08
    çļĦäºĭäºĨ
    0.08
    ãģ¸ãģ®
    0.08
    æĪijä¹Łè¦ģ
    0.08
    çļĦ使çĶ¨
    0.08
    çļĦ建ç«ĭ
    0.07
    ä¹ĭäºī
    0.07
    å·¥ä½ľçļĦå¼Ģå±ķ
    0.07
    Activations Density 0.915%

    No Known Activations