© 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. 41113
    Prev
    Next
    INDEX
    Explanations

    learning or struggling with basics

    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
    áĢ¶
    -0.09
    ä¸įè°Ī
    -0.08
    æĽ´å¥½åľ°äºĨ解
    -0.07
    ä½İè°ĥ
    -0.07
    å¯ĨåĪĩæݥ触
    -0.07
    ariat
    -0.07
    å¼Ģå¹ķ
    -0.07
    å¾Ĺ罪
    -0.07
     menyus
    -0.07
    ุล
    -0.07
    POSITIVE LOGITS
    å·©åĽº
    0.10
     textbook
    0.08
     struggling
    0.08
     textbooks
    0.08
     Basic
    0.08
    åŃ¦å¥½
    0.07
    å¬Į
    0.07
    Basic
    0.07
    ctal
    0.07
    åѦç¿Ĵ
    0.07
    Activations Density 0.154%

    No Known Activations