© 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. 25377
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
    unsch
    -0.08
    opedia
    -0.07
    æ¸Ĭæĺİ
    -0.07
    诸侯
    -0.06
    æīİ
    -0.06
    اÙģÛĮ
    -0.06
    atik
    -0.06
    è¸ıæŃ¥
    -0.06
    æĹłæŃ¢
    -0.06
    .debian
    -0.06
    POSITIVE LOGITS
    æĪİ
    0.08
    ouden
    0.07
    ISR
    0.07
    éģĵ
    0.07
    escription
    0.07
    umus
    0.07
    /lab
    0.07
    ÑģÑĤо
    0.07
    usal
    0.07
    ots
    0.07
    Activations Density 0.002%

    No Known Activations