© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9306
    Prev
    Next
    INDEX
    Explanations

    Mexican places and authorities

    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
     Mercy
    -0.10
    2
    -0.09
    夺åıĸ
    -0.09
    0
    -0.09
     Sequelize
    -0.09
    çijŀ士
    -0.09
    8
    -0.09
    4
    -0.08
    顺德
    -0.08
     cram
    -0.08
    POSITIVE LOGITS
    墨西åĵ¥
    0.12
     Mex
    0.12
     Mexican
    0.11
     Mexicans
    0.11
     Mexico
    0.11
    Mexico
    0.10
    .mx
    0.10
    éĢĢ
    0.10
    otle
    0.10
     OECD
    0.10
    Activations Density 0.159%

    No Known Activations