© 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. 47989
    Prev
    Next
    INDEX
    Explanations

    questions about existence or characteristics

    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
    stad
    -0.07
     Soares
    -0.07
    åĨįæİ¥åĨį
    -0.06
    ål
    -0.06
     Zaragoza
    -0.06
    群éĽĦ
    -0.06
    Ø°Ùĩ
    -0.06
    gow
    -0.06
    äºĨèĩªå·±çļĦ
    -0.06
    æİĢèµ·
    -0.06
    POSITIVE LOGITS
     cioè
    0.07
    nano
    0.07
     infatti
    0.07
    ä¸įä»ħæľī
    0.07
     pousser
    0.07
    ä»Ģä¹Ī人
    0.07
     bowiem
    0.06
    ä¼ļæĽ´å¥½
    0.06
     simply
    0.06
    ãģ©ãĤĮãģłãģij
    0.06
    Activations Density 0.217%

    No Known Activations