© 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. 51739
    Prev
    Next
    INDEX
    Explanations

    `.split` followed by delimiter or `()` or lines

    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
    lease
    -0.07
    æĭ±æīĭ
    -0.06
    ews
    -0.06
    uts
    -0.06
    ç»ıæµİä¸İ
    -0.06
    Attachments
    -0.06
    ç»´æĬ¤åĴĮ
    -0.06
    _EXISTS
    -0.06
     Fowler
    -0.06
    _FMT
    -0.06
    POSITIVE LOGITS
    Ð¢ÐŁ
    0.08
    çļĦ人è¿ĺ
    0.08
    à¹Ģà¸ĸ
    0.08
    tabs
    0.07
    ennen
    0.07
    erings
    0.07
    æľĥéķ·
    0.07
    works
    0.07
    سÙĬ
    0.07
    uur
    0.07
    Activations Density 0.001%

    No Known Activations