© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30464
    Prev
    Next
    INDEX
    Explanations

    Egypt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åĬłçĽŁ
    -0.10
    è¾ĸåĮº
    -0.09
    好çľĭ
    -0.09
    æµģåĬ¨
    -0.09
    天çĶŁ
    -0.09
    大å®ĹåķĨåĵģ
    -0.09
    çijŀ士
    -0.09
    RM
    -0.09
    è°ı
    -0.08
    è¹ĩ
    -0.08
    POSITIVE LOGITS
    åŁĥåıĬ
    0.17
    Egypt
    0.15
     Egyptian
    0.15
     Egypt
    0.13
     Egyptians
    0.12
    gypt
    0.11
     Nile
    0.11
     اÙĦÙħصرÙĬ
    0.10
     اÙĦÙħصرÙĬØ©
    0.10
    æĸĩæĺİ
    0.09
    Activations Density 0.053%

    No Known Activations