© 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. 11029
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with derivatives

    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
    売
    -0.07
     Spo
    -0.06
     Wet
    -0.06
    çļĦåħīèį£
    -0.06
     Sus
    -0.06
    æĮij
    -0.06
    èį£åįİ
    -0.06
    /host
    -0.06
    ç¥ĸåĽ½
    -0.06
     Sust
    -0.06
    POSITIVE LOGITS
    imia
    0.08
    viz
    0.08
    ÛĮرÙĩ
    0.08
    à¸Ħร
    0.07
    coni
    0.07
    lee
    0.07
    èche
    0.07
    fax
    0.07
    odem
    0.07
    ulg
    0.07
    Activations Density 0.175%

    No Known Activations