© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    degree or extent

    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
    çľ¼å¸ĺ
    -0.09
    该éĻ¢
    -0.07
    .ads
    -0.07
    åĵij
    -0.07
    esel
    -0.06
     ayr
    -0.06
    åıĪ被
    -0.06
    欢è¿İæĤ¨çļĦ
    -0.06
    Rep
    -0.06
    åİĤåĮº
    -0.06
    POSITIVE LOGITS
    æŁIJ人
    0.10
    æŁIJ
    0.08
    æŁIJ个
    0.08
     somebody
    0.07
     someone
    0.07
     oneself
    0.07
    amá
    0.07
    asto
    0.07
    ä¸ŀ
    0.07
    wg
    0.07
    Activations Density 0.027%

    No Known Activations