© 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. 59932
    Prev
    Next
    INDEX
    Explanations

    main thing, Editorial, Islamic, many, unified

    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
    好æŃ¹
    -0.09
    åİ¿å§Ķåī¯ä¹¦è®°
    -0.08
    åºĶå°½éĩı
    -0.08
    å¹²èĦĨ
    -0.08
    责任å¿ĥ强
    -0.07
    åľ¨ç¾İ
    -0.07
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.07
    å°½éĩıä¸įè¦ģ
    -0.07
    ço
    -0.07
    å°½éĩı
    -0.07
    POSITIVE LOGITS
    éĺIJ
    0.08
    çļĦåĨħ涵
    0.08
     unprecedented
    0.08
    çħ§èĢĢ
    0.08
    çļĦéĩįè¦ģ举æݪ
    0.08
     proclaimed
    0.08
    æ²»åĽ½
    0.08
    宣è¨Ģ
    0.07
    æ±²åıĸ
    0.07
    åĨħ涵
    0.07
    Activations Density 0.002%

    No Known Activations