© 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. 9083
    Prev
    Next
    INDEX
    Explanations

    air pollution and emissions

    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
    æĬµæĬĹ
    -0.10
    aal
    -0.10
    æĥħå½¢
    -0.09
    代表
    -0.09
    ä¸Ģæŀļ
    -0.09
    Ùħار
    -0.09
    åĩºåħ¥
    -0.09
    欣åĸľ
    -0.09
    åºŁçī©
    -0.09
    represent
    -0.09
    POSITIVE LOGITS
    åĭ
    0.09
    aments
    0.08
    .jupiter
    0.08
    Lines
    0.08
     jane
    0.08
    人æ°ij
    0.08
     Delhi
    0.08
    AMENT
    0.08
    èĭĭ
    0.08
    ament
    0.07
    Activations Density 0.054%

    No Known Activations