© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 580
    Prev
    Next
    INDEX
    Explanations

    international / countries

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     statewide
    -0.29
     holland
    -0.27
    åŁºè¾ħ
    -0.25
     italian
    -0.25
     Saudis
    -0.24
    EFAULT
    -0.24
    åIJĮåŁİ
    -0.24
     ohio
    -0.24
    AuthGuard
    -0.22
     Tunis
    -0.22
    POSITIVE LOGITS
     countries
    0.46
     international
    0.44
    åIJĦåĽ½
    0.44
    åĽ½éĻħ
    0.41
     global
    0.40
    åħ¨çIJĥ
    0.39
    çļĦä¸ĸçķĮ
    0.35
    countries
    0.35
     world
    0.34
    global
    0.34
    Activations Density 5.410%

    No Known Activations