© 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. 51575
    Prev
    Next
    INDEX
    Explanations

    stations, stores, and dispensing locations

    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
    大桥
    -0.10
    é®
    -0.10
    ầu
    -0.10
     spons
    -0.09
     liá»ģn
    -0.09
    .Factory
    -0.09
    åģıåģı
    -0.09
    ä¸įæĺ¯ä¸Ģ个
    -0.09
    å¾Ī大çļĦ
    -0.09
    å²Ń
    -0.09
    POSITIVE LOGITS
    hits
    0.10
    hit
    0.09
    ItemCount
    0.09
    oner
    0.09
    缯
    0.08
    ICA
    0.08
    åľ¨çº¿
    0.08
    åĢ¼çıŃ
    0.08
    åIJĮå¿Ĺ们
    0.08
    åľ¨èģĮ
    0.08
    Activations Density 0.006%

    No Known Activations