© 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. 50405
    Prev
    Next
    INDEX
    Explanations

    `#include` statement

    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
    å¼Ĥ
    -0.08
    çķ°
    -0.07
    填满
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    åħį费订éĺħ
    -0.07
    ég
    -0.06
    æĸ°ä¹¦æݨèįIJ
    -0.06
    лдÑĭ
    -0.06
    åĨħ容æıIJä¾Ľæĸ¹
    -0.06
    entic
    -0.06
    POSITIVE LOGITS
    oute
    0.08
    vento
    0.07
    并èĮĤ
    0.07
    并
    0.07
    并æĮīçħ§
    0.07
    Ïĩε
    0.07
    zus
    0.07
    并æĬĬ
    0.07
    সà§įয
    0.07
    amed
    0.06
    Activations Density 0.261%

    No Known Activations