© 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. 57003
    Prev
    Next
    INDEX
    Explanations

    page numbers and citations

    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
    ry
    -0.08
    mq
    -0.07
    ype
    -0.07
    æĹ¢çĦ¶
    -0.07
    /trunk
    -0.06
    æĿ¥è¶Ĭ
    -0.06
    RY
    -0.06
    LOS
    -0.06
    åĵ¼
    -0.06
     mathematic
    -0.06
    POSITIVE LOGITS
    åħ¨åĬĽåģļ好
    0.08
    è¿Ļ个女人
    0.07
    åĴĮä¸Ń
    0.07
    ản
    0.07
    weekly
    0.07
    Bahn
    0.07
    æŬ
    0.07
    Weekly
    0.07
     suppl
    0.07
    atoon
    0.07
    Activations Density 0.019%

    No Known Activations