© 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. 51191
    Prev
    Next
    INDEX
    Explanations

    laboratory or medical parameters

    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
     sÆ°á»Łi
    -0.07
    åı¯ä»¥æĶ¹åĸĦ
    -0.07
    ubi
    -0.07
    ÐijУ
    -0.06
    åıĸæļĸ
    -0.06
    ä¹Łåĸľæ¬¢
    -0.06
    ÐĹÐŀ
    -0.06
    è·¯éĢı
    -0.06
    ubro
    -0.06
    åıijå±ķæľºéģĩ
    -0.06
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.08
    olarity
    0.08
    å¯Ĩ度
    0.07
    æµĵ度
    0.07
    é«ĺå¯Ĩ
    0.07
    èIJ±
    0.07
    ourney
    0.07
    imid
    0.07
    ystore
    0.07
     potency
    0.07
    Activations Density 0.002%

    No Known Activations