© 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. 44769
    Prev
    Next
    INDEX
    Explanations

    comparison, simultaneity, combination, or equality

    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
    tot
    -0.07
    ä»Ĺ
    -0.07
     Pessoa
    -0.07
    .addTo
    -0.07
    ADATA
    -0.07
    ä¸İå°ı
    -0.07
    ä¹IJåĽ¢
    -0.07
    ÑĢоÑĤ
    -0.06
    å¤įåIJĪåŀĭ
    -0.06
    xis
    -0.06
    POSITIVE LOGITS
     beiden
    0.13
    çļĦ两个
    0.12
    çĶ·å¥³
    0.12
    æĸ°æŧ
    0.12
    两ç§į
    0.11
     two
    0.11
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.11
    室åĨħå¤ĸ
    0.11
    å·¦åı³
    0.11
    两类
    0.11
    Activations Density 0.332%

    No Known Activations