© 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. 30272
    Prev
    Next
    INDEX
    Explanations

    world, this, slightly, likewise, similarly

    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
     mot
    -0.07
    åĽ¢åĽ¢
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    wai
    -0.07
    jul
    -0.07
     parla
    -0.07
    å¸ĥæĸ¯
    -0.07
    éĥ½ä¸į太
    -0.07
    (exports
    -0.07
    osl
    -0.07
    POSITIVE LOGITS
    åIJĮæł·
    0.13
    ä¸İä¹ĭ
    0.12
    åIJĮæł·çļĦ
    0.12
     similarly
    0.11
    åIJĮæł·æĺ¯
    0.10
     likewise
    0.10
    åIJĮ樣
    0.10
     hingegen
    0.09
     Similarly
    0.09
     stej
    0.09
    Activations Density 0.280%

    No Known Activations