© 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. 23656
    Prev
    Next
    INDEX
    Explanations

    RS, .xls, Array, money, liquid, Number, $

    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
     atleast
    -0.07
    á»Ĺ
    -0.07
    .experimental
    -0.06
    交æīĢ
    -0.06
     add
    -0.06
    add
    -0.06
     Add
    -0.06
    utters
    -0.06
    Ø°Ùĩ
    -0.05
    ä¸İåĪĽæĸ°
    -0.05
    POSITIVE LOGITS
    Prov
    0.08
    finalize
    0.08
    人æĪĸ
    0.08
    ìĸ´ëĤĺ
    0.07
    åŁİ乡建设
    0.07
    epar
    0.07
    llib
    0.07
    éĵ¶ä¿Ŀ
    0.07
    æĭĨå¼Ģ
    0.07
    åĴĮæĻ®éĢļ
    0.07
    Activations Density 0.002%

    No Known Activations