© 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. 2016
    Prev
    Next
    INDEX
    Explanations

    Arabic and Middle Eastern 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
    ,
    -0.07
     Jiang
    -0.06
     Vietnam
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    å¸
    -0.06
     Vietnamese
    -0.06
    ogen
    -0.05
     India
    -0.05
    Crypt
    -0.05
     Chennai
    -0.05
    POSITIVE LOGITS
     ÑĪей
    0.09
     Ibnu
    0.09
    brahim
    0.09
     Ejem
    0.09
     Ibn
    0.09
    gypt
    0.09
     Mahmoud
    0.09
    aleb
    0.09
     Ả
    0.09
     Libyan
    0.09
    Activations Density 0.284%

    No Known Activations