© 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. 65143
    Prev
    Next
    INDEX
    Explanations

    yields, funds, market, bond, US dollars

    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
    åŀ¢
    -0.07
    меÑĢов
    -0.07
    ful
    -0.07
    imente
    -0.07
    .original
    -0.06
    lÄħ
    -0.06
    èIJ½æĹ¥
    -0.06
    xca
    -0.06
    Ļ
    -0.06
    åĴ¬çīĻåĪĩ
    -0.06
    POSITIVE LOGITS
    upan
    0.08
    ouer
    0.08
    à¸ķิ
    0.08
    Rates
    0.07
    æ®ĸ
    0.07
    ÏĦιÏĥ
    0.07
    .flash
    0.07
    åŁºåĩĨåĪ©çİĩ
    0.07
    æĺİ示
    0.07
     Pon
    0.07
    Activations Density 0.002%

    No Known Activations