© 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. 3784
    Prev
    Next
    INDEX
    Explanations

    political and economic contexts

    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
    å°ĨæĿ¥çļĦ
    -0.08
    ompiler
    -0.08
    ä¸įåı¯ç¼ºå°ij
    -0.08
    åľ¨ä»ĬåIJİçļĦ
    -0.07
     nanti
    -0.07
    contra
    -0.07
    dbh
    -0.07
     someday
    -0.07
     hopefully
    -0.07
    å¥½å¥½åľ°
    -0.07
    POSITIVE LOGITS
    缺ä¹ı
    0.09
    追æ±Ĥ
    0.09
    å¾Ģå¾Ģ
    0.09
    è¯Ħä»·ä½ĵç³»
    0.09
    åĬ¨è¾Ħ
    0.09
    å¾Ģå¾Ģæĺ¯
    0.08
    ä¹łæĥ¯äºİ
    0.08
    è¿Ļ使å¾Ĺ
    0.08
    è¿ĩå¤ļçļĦ
    0.08
    æĢ¥äºİ
    0.08
    Activations Density 0.046%

    No Known Activations