© 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. 62981
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by special characters

    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
    Ùĩ
    -0.12
    ly
    -0.10
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
    ìĹIJ
    -0.08
    çļĦ
    -0.08
    ìĿĦ
    -0.08
    à¥Ĥ
    -0.08
    ×ķ
    -0.08
    os
    -0.07
    d
    -0.07
    POSITIVE LOGITS
    edException
    0.10
    åħ¼æĢ»ç»ıçIJĨ
    0.09
    lessly
    0.09
    ìĦľëĬĶ
    0.09
    ktan
    0.08
    andest
    0.08
    alse
    0.08
    ermal
    0.08
    unar
    0.08
    åĻ¨åĴĮ
    0.08
    Activations Density 0.003%

    No Known Activations