© 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. 52004
    Prev
    Next
    INDEX
    Explanations

    how do I

    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
    aved
    -0.06
    achten
    -0.06
     taraf
    -0.06
     ÙĩÙħاÙĨ
    -0.06
    åĶ¾
    -0.06
    alian
    -0.06
    оÑĢа
    -0.06
    äºĭ
    -0.06
    æīĢæĮģ
    -0.06
    åľ¨æīĢ
    -0.06
    POSITIVE LOGITS
    éĿ¢éĿ¢
    0.07
    áĥĿáĥĵ
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    æ¯Ķè¾ĥ好çļĦ
    0.07
    ød
    0.07
    ä¸ŃèĦ±é¢ĸèĢĮåĩº
    0.07
    åĸľæ¬¢ä¸Ĭ
    0.07
    evere
    0.07
    ãĥ¼ãĤ¹
    0.07
    udden
    0.07
    Activations Density 0.094%

    No Known Activations