© 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. 15101
    Prev
    Next
    INDEX
    Explanations

    medical conditions with "-opathy"

    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
    what
    -0.06
     tant
    -0.06
    Ïį
    -0.06
    .
    -0.05
    触çĬ¯
    -0.05
    åijĪ
    -0.05
     what
    -0.05
    laughter
    -0.05
    åĬ¨
    -0.05
    è¿Ļä¸ĭ
    -0.05
    POSITIVE LOGITS
     similarly
    0.12
    ä¹Łæĺ¯å¦ĤæѤ
    0.11
     likewise
    0.11
    亦çĦ¶
    0.10
     ë§Īì°¬ê°Ģì§Ģë¡ľ
    0.10
    ä¹Łæĺ¯ä¸Ģæł·
    0.10
     ë§Īì°¬ê°Ģì§Ģ
    0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    0.10
    åIJĮæł·æĺ¯
    0.10
    åIJĮ樣
    0.09
    Activations Density 0.212%

    No Known Activations