© 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. 60048
    Prev
    Next
    INDEX
    Explanations

    non-latin characters or punctuation followed by text

    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
    visor
    -0.07
    ährungs
    -0.07
    ä½ĵèĤ²åľº
    -0.07
    ivor
    -0.07
    ä»ĸè¿ĺæĺ¯
    -0.07
    代ä¼ļ
    -0.07
    çݯä¿Ŀå±Ģ
    -0.06
    娥
    -0.06
    à¸Ķย
    -0.06
    agentur
    -0.06
    POSITIVE LOGITS
    aho
    0.08
    oha
    0.07
    eca
    0.07
     занÑıÑĤие
    0.07
    æľīä½į
    0.07
    à¹īย
    0.07
    ÏĦαν
    0.07
    ег
    0.06
     marty
    0.06
    ä¸Ģç¯ĩ
    0.06
    Activations Density 0.003%

    No Known Activations