© 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. 16517
    Prev
    Next
    INDEX
    Explanations

    run, execute, apply, computation

    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
    SURE
    -0.08
    YRO
    -0.08
    UDE
    -0.07
     earm
    -0.07
    ¥
    -0.07
    è¦ģç»ı常
    -0.07
    ategoria
    -0.07
    æĪĺçķ¥æĢ§
    -0.07
    Assignable
    -0.07
    è¿Ļç§įçݰ象
    -0.07
    POSITIVE LOGITS
    ä¸¥æł¼æĮīçħ§
    0.10
     faithfully
    0.10
    æĮīçħ§
    0.09
    å¿łå®ŀ
    0.09
    æī§è¡Į
    0.08
    计ç®Ĺ
    0.08
     computation
    0.08
     ìĪĺíĸī
    0.08
    è¨
    0.08
    åºĶå½ĵæĮīçħ§
    0.07
    Activations Density 0.080%

    No Known Activations