© 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. 18174
    Prev
    Next
    INDEX
    Explanations

    Portuguese names and places

    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
    èĬĿåĬłåĵ¥
    -0.11
    ônicas
    -0.10
     Illinois
    -0.10
    Chicago
    -0.09
    гоÑĤо
    -0.09
    èĭĩ
    -0.09
    ônio
    -0.09
     Chicago
    -0.09
    Minnesota
    -0.09
    undra
    -0.09
    POSITIVE LOGITS
    èij¡èIJĦçīĻ
    0.13
    èij¡
    0.12
     Portugal
    0.12
     portugueses
    0.11
     Portuguese
    0.11
     portug
    0.11
    æ¾³éŨ
    0.10
    æ¾³éĸĢ
    0.10
     Lisbon
    0.09
     ÐŁÐ¾ÑĢÑĤÑĥ
    0.09
    Activations Density 0.114%

    No Known Activations