© 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. 27446
    Prev
    Next
    INDEX
    Explanations

    mathematical variables (n, k, d, m)

    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
    æľŁä¸º
    -0.07
    δα
    -0.07
    ä¼ĺ
    -0.07
    -online
    -0.06
     projected
    -0.06
    law
    -0.06
    以ä¸ĭåĩłçĤ¹
    -0.06
    æķı
    -0.06
    æİ¥åĬĽ
    -0.06
    ilor
    -0.06
    POSITIVE LOGITS
    æĥ«
    0.08
     determined
    0.08
     odre
    0.07
    æĺ¯æľĢ大çļĦ
    0.07
    åĩıåİĭ
    0.07
    _walk
    0.07
    à¹ģà¸Ļ
    0.07
    说æĺİ
    0.07
    ç¡®å®ļ为
    0.07
    æĺ¯åĶ¯ä¸Ģ
    0.07
    Activations Density 0.007%

    No Known Activations