© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34900
    Prev
    Next
    INDEX
    Explanations

    definition of the

    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
    Negative Logits
    åij½åIJį为
    -0.09
    èµĦæºIJä¼ĺåĬ¿
    -0.09
    egrity
    -0.08
    ţe
    -0.08
    èı²å¾ĭ
    -0.08
    ä¸ĸçķĮåĨłåĨĽ
    -0.08
    zzi
    -0.08
    äºĨèĩªå·±çļĦ
    -0.08
    rink
    -0.08
    ä¿¡æģ¯çŃī
    -0.08
    POSITIVE LOGITS
    è¡¡
    0.10
    è¿Ļæł·ä¸Ģç§į
    0.09
    ä¸Ģç§į
    0.08
    æ³ĽæĮĩ
    0.08
    çļĦä¸Ģç§į
    0.08
     aquella
    0.07
    å°±æĺ¯æĮĩ
    0.07
     when
    0.07
     olyan
    0.07
    when
    0.07
    Activations Density 0.163%

    No Known Activations