© 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. 19871
    Prev
    Next
    INDEX
    Explanations

    churches and religious organizations

    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
    驽
    -0.10
    åģļ梦
    -0.09
     Malone
    -0.09
    ucher
    -0.09
    mie
    -0.09
    顶å±Ĥ设计
    -0.08
    å§IJå§IJ
    -0.08
    æĥħæĬ¥
    -0.08
    azz
    -0.08
    éķĢéĶĮ
    -0.08
    POSITIVE LOGITS
    人人
    0.10
    ä¿®åħ»
    0.08
    è¯ļå®ŀ
    0.08
    è¯ļ
    0.08
    社åĮº
    0.08
     pirates
    0.08
    ÑĤок
    0.08
    交éĢļ
    0.08
    ç«Ļ
    0.07
    æ²¹
    0.07
    Activations Density 0.045%

    No Known Activations