© 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. 52119
    Prev
    Next
    INDEX
    Explanations

    key component/role/contributor/element/technology/player/regulator

    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
    abar
    -0.08
     strictly
    -0.07
    ä¸įå°ıå¿ĥ
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    æĦ
    -0.06
    æīĭæľºå®¢æĪ·ç«¯
    -0.06
    unga
    -0.06
    严éĩįæŶ
    -0.06
    ull
    -0.06
    ienne
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸ĢçļĦ
    0.13
    ä¹ĭä¸Ģ
    0.12
    ä¹ĭä¸Ģæĺ¯
    0.10
    ä¹ĭä¸Ģå°±æĺ¯
    0.10
    èİ«è¿ĩäºİ
    0.08
    stay
    0.08
    åľ¨äºİ
    0.08
     ترÛĮÙĨ
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    ä¸Ģçݯ
    0.08
    Activations Density 0.184%

    No Known Activations