© 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. 28197
    Prev
    Next
    INDEX
    Explanations

    interest rate or APR percentage

    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
    Ñģпен
    -0.07
    éĿ¢ç§¯çļĦ
    -0.06
    à´±àµĨ
    -0.06
    æİĴ便
    -0.06
     Investigations
    -0.06
     volumes
    -0.06
    AVED
    -0.06
    ึà¸ģ
    -0.06
    ancias
    -0.06
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.06
    POSITIVE LOGITS
     rate
    0.12
    å¹´åĪ©çİĩ
    0.11
     Rate
    0.11
    _rate
    0.11
    rate
    0.10
    æģ¯
    0.10
    .rate
    0.10
    Rate
    0.09
     annum
    0.09
     rates
    0.09
    Activations Density 0.015%

    No Known Activations