© 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. 10687
    Prev
    Next
    INDEX
    Explanations

    layout: blog post

    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
    xlsx
    -0.08
    .sourceforge
    -0.08
    .xlsx
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.08
     census
    -0.07
    çĥŃæIJľè¯į
    -0.07
    æķĻèĤ²ç½ij
    -0.07
    .rar
    -0.07
    åĨ»
    -0.07
    POSITIVE LOGITS
     blog
    0.10
     content
    0.09
    .blog
    0.09
     topics
    0.09
     blogs
    0.09
     articles
    0.09
    æĸĩç«ł
    0.09
    blog
    0.08
    -topic
    0.08
    (Content
    0.08
    Activations Density 0.672%

    No Known Activations