© 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. 22824
    Prev
    Next
    INDEX
    Explanations

    Graves disease

    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
    éĻĪ代谢
    -0.08
    Qualifier
    -0.08
    ).__
    -0.08
    è¶ħåĩ¡
    -0.08
    æĸ°äº¬
    -0.08
    à¸ĵ
    -0.07
    鼶åħ«
    -0.07
    /fw
    -0.07
    öny
    -0.07
    éĢłæĪIJ伤害
    -0.07
    POSITIVE LOGITS
    éī´åĪ«
    0.09
    åįķ纯
    0.08
    ç¥ĸåĽ½
    0.08
    åįĬæķ°
    0.07
    è¯ī说
    0.07
    å°ıå²Ľ
    0.07
    ä¸ĺ
    0.07
    åĺ±
    0.07
    è¿ģ
    0.07
    WHO
    0.07
    Activations Density 0.054%

    No Known Activations