© 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. 22311
    Prev
    Next
    INDEX
    Explanations

    100 percent or %

    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
    ستاÙĨÛĮ
    -0.09
    à§įষ
    -0.09
     degusta
    -0.08
    æĪĸèĢħ缴æİ¥
    -0.08
    微信æī«ä¸Ģæī«
    -0.08
    ioned
    -0.08
    iators
    -0.08
    isah
    -0.08
    کا
    -0.08
    lemi
    -0.08
    POSITIVE LOGITS
    çĴŀ
    0.07
    ãģ«è¿ijãģĦ
    0.07
    esis
    0.07
    ï¸ı
    0.06
    è¿ijãģı
    0.06
    缴
    0.06
     ÐĹаÑĩ
    0.06
    -
    0.05
    /close
    0.05
    >
    0.05
    Activations Density 0.050%

    No Known Activations