© 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. 22611
    Prev
    Next
    INDEX
    Explanations

    sales, discounts, coupons

    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
    icus
    -0.07
    åįĴ
    -0.07
     Abstract
    -0.07
    	Copyright
    -0.06
    å¤ĸåĮħ
    -0.06
     travers
    -0.06
    åĥ
    -0.06
    åIJĪ秣
    -0.06
     вÑģÑĤа
    -0.06
    ä¼ļåijĺæľįåĬ¡
    -0.06
    POSITIVE LOGITS
     promotions
    0.11
     discounts
    0.11
    让åĪ©
    0.11
    ä¼ĺæĥł
    0.11
    ä¿ĥéĶĢ
    0.11
     Ски
    0.10
     discount
    0.10
    æĬĺæī£
    0.10
     promotional
    0.10
    discount
    0.10
    Activations Density 0.127%

    No Known Activations