© 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. 63673
    Prev
    Next
    INDEX
    Explanations

    regular expressions and specific chemical/language terms

    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
    èħĶ
    -0.08
    æį¢åı¥è¯Ŀ说
    -0.07
    houd
    -0.07
    ä¼Ĭæĸ¯
    -0.07
    inkin
    -0.07
    ä¸īæĽ´
    -0.07
    enen
    -0.07
     Decomp
    -0.07
    unas
    -0.07
    家æĺ¯
    -0.07
    POSITIVE LOGITS
    änk
    0.08
    /rand
    0.07
    enberg
    0.07
    PL
    0.07
    uit
    0.06
    åħ®
    0.06
    /connect
    0.06
    /*!
    0.06
    æŁ
    0.06
    uddle
    0.06
    Activations Density 0.261%

    No Known Activations