© 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. 60811
    Prev
    Next
    INDEX
    Explanations

    bibliography

    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
    appar
    -0.07
    yii
    -0.07
    /testify
    -0.07
    ãģ«ãģªãĤīãģªãģĦ
    -0.07
    irim
    -0.06
    bling
    -0.06
    uren
    -0.06
    à¸ķู
    -0.06
    AZY
    -0.06
    ystack
    -0.06
    POSITIVE LOGITS
     file
    0.19
    æĸĩ件
    0.19
    æĸĩ件åĴĮ
    0.16
     files
    0.15
     ÑĦайл
    0.15
    æĸĩ件ä¸Ń
    0.15
    æĸĩ件çļĦ
    0.15
    -file
    0.15
     íĮĮìĿ¼ìĿĦ
    0.14
    ãĥķãĤ¡ãĤ¤ãĥ«
    0.14
    Activations Density 1.450%

    No Known Activations