© 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. 52118
    Prev
    Next
    INDEX
    Explanations

    addition or inclusion

    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
    ARGV
    -0.07
     Dual
    -0.07
    agma
    -0.07
    Dual
    -0.07
    æļ´åĪ©
    -0.07
     jolie
    -0.07
    ä¸įäºĨ
    -0.07
    aced
    -0.07
    orna
    -0.07
     ëĭ
    -0.06
    POSITIVE LOGITS
     contributions
    0.13
    è´¡çĮ®
    0.09
    æĿ¥èĩª
    0.09
    æĿ¥èĩªäºİ
    0.09
     whatever
    0.09
    鼶鼶
    0.09
     contribution
    0.09
     ÑģобÑģÑĤвенно
    0.08
     Contributions
    0.08
    çļĦè´¡çĮ®
    0.08
    Activations Density 0.021%

    No Known Activations