© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50786
    Prev
    Next
    INDEX
    Explanations

    Amazon, Brazil, South America

    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
    éŁŃ
    -0.10
     Loch
    -0.09
     Mediterranean
    -0.08
    ews
    -0.08
     ÙĪاÙĦØŃ
    -0.08
    éĻĮ
    -0.08
    éªħ
    -0.08
    Trim
    -0.08
    éĺ¿å¯Įæ±Ĺ
    -0.08
    ("/{
    -0.08
    POSITIVE LOGITS
    äºļ马éĢĬ
    0.11
     jungle
    0.10
    åıĻ
    0.10
     Amazon
    0.09
    èģĬåŁİ
    0.09
    Brazil
    0.09
    巴西
    0.09
    umas
    0.09
     Brazilian
    0.09
    寮
    0.09
    Activations Density 0.185%

    No Known Activations