© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14623
    Prev
    Next
    INDEX
    Explanations

    adverbial endings like -ally, -ically

    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
    ÑģнÑĭ
    -0.08
    æŁIJ天
    -0.08
    ä¹ĭåIJİå°±
    -0.07
    AZE
    -0.07
    ernals
    -0.07
    å¦į
    -0.07
    ä¸Ģ女
    -0.07
    ä¹Łåı«
    -0.07
    æķħåIJį
    -0.07
    Locator
    -0.07
    POSITIVE LOGITS
    æĸ¹éĿ¢
    0.11
    èĢĮè¨Ģ
    0.10
     же
    0.09
    æĿ¥è¯´
    0.09
    ìłģìľ¼ë¡ľëĬĶ
    0.09
     thì
    0.09
    ä¾Ĩ說
    0.08
     ÙģØ¥ÙĨ
    0.08
    çļĦè¯Ŀ
    0.08
    ìľ¼ë¡ľëĬĶ
    0.08
    Activations Density 0.193%

    No Known Activations