© 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. 41212
    Prev
    Next
    INDEX
    Explanations

    action verbs after conjunctions

    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
    起身
    -0.08
    鼷æĸ¯
    -0.07
    èµ·åºĬ
    -0.07
    earer
    -0.07
    ìļ°
    -0.07
    æµģè¿ŀ
    -0.06
    otte
    -0.06
    çĤ¹åĩ»è¿Ľåħ¥
    -0.06
    åĩºåĬ¨
    -0.06
    ek
    -0.06
    POSITIVE LOGITS
    å¯Ĩä¸įåı¯
    0.09
     Beit
    0.08
    Americ
    0.07
    ä¹Łæĺ¯ä¸Ģæł·
    0.07
    åѦéĩij
    0.07
    详ç»ĨäºĨ解
    0.07
    θεν
    0.07
    ðŁĻĤ
    0.07
    并ä¸įçŁ¥éģĵ
    0.07
    详
    0.07
    Activations Density 0.347%

    No Known Activations