© 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. 34897
    Prev
    Next
    INDEX
    Explanations

    diagonal type algebras

    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
    æīij
    -0.08
    é«ĺè´¨éĩı
    -0.08
     ìłij
    -0.08
     Servic
    -0.08
    formance
    -0.07
    é«ĺè´¨éĩıçļĦ
    -0.07
    elib
    -0.07
    飧æĢ§
    -0.07
    ÑĪиб
    -0.07
    ä¸įçŁ¥éģĵçļĦ
    -0.07
    POSITIVE LOGITS
    åĮĹè¾°
    0.07
    è±
    0.07
     slicing
    0.06
     favourites
    0.06
    ä¸¥æł¼æݧåĪ¶
    0.06
    主轴
    0.06
    à¹Ģà¸Ĺีà¹Īย
    0.06
    -wise
    0.06
    okr
    0.06
    itter
    0.06
    Activations Density 0.003%

    No Known Activations