© 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. 7217
    Prev
    Next
    INDEX
    Explanations

    how it can be

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èĸĩ
    -0.08
    æĺ¯ä»Ģä¹Īåij¢
    -0.07
    çĴ¨
    -0.07
    usc
    -0.07
    اتب
    -0.06
    æĹłçĸij
    -0.06
    itized
    -0.06
    åı¯ä»¥åIJĹ
    -0.06
    Unhandled
    -0.06
     Knob
    -0.06
    POSITIVE LOGITS
     ÙĪØ£ÙĨÙĩ
    0.12
    以åıĬå¦Ĥä½ķ
    0.11
     ÙĪÙĥÙĬÙģ
    0.10
    并举
    0.09
    举ä¾ĭ
    0.09
    æĢ§ä»¥åıĬ
    0.08
    å¦Ĥä½ķéĢļè¿ĩ
    0.08
     ìŀĪìĿĮìĿĦ
    0.08
    并æıIJåĩº
    0.08
    ä¸įäºī
    0.08
    Activations Density 0.032%

    No Known Activations