© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48904
    Prev
    Next
    INDEX
    Explanations

    rare conditions

    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
    ippi
    -0.08
    .cls
    -0.08
    对äºİä¸Ģ个
    -0.08
    opus
    -0.07
    çī¹æĸ°
    -0.07
     sole
    -0.07
     Reed
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    å·¥åķĨ
    -0.07
    ç´łè´¨åĴĮ
    -0.07
    POSITIVE LOGITS
    éĹ´æİ¥
    0.08
     indirectly
    0.08
     indirect
    0.07
    两ä¸į误
    0.07
    ervi
    0.07
    åIJĽ
    0.07
    åĪĨ寸
    0.06
    _rm
    0.06
    ä»ĸèĩªå·±çļĦ
    0.06
    æ¯ĶæĭŁ
    0.06
    Activations Density 0.346%

    No Known Activations