© 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. 26779
    Prev
    Next
    INDEX
    Explanations

    taxes, tariffs, rates, percentages

    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
    chk
    -0.07
    .exports
    -0.07
    toj
    -0.07
    qip
    -0.07
    izm
    -0.07
    ujo
    -0.07
    èªĮ
    -0.07
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    -0.07
    æĪIJç«ĭçļĦ
    -0.06
    ä»»ä½ķä¿Ŀè¯ģ
    -0.06
    POSITIVE LOGITS
     tier
    0.11
     tiers
    0.10
    -tier
    0.09
     lev
    0.09
    lev
    0.09
    ç¨İçİĩ
    0.09
     applicable
    0.09
     applied
    0.09
     rates
    0.09
    ä¸Ģæ¡£
    0.09
    Activations Density 0.040%

    No Known Activations