© 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. 37480
    Prev
    Next
    INDEX
    Explanations

    preach, preacher, advocate, lecture

    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
    ework
    -0.10
    æī¿
    -0.10
    assed
    -0.09
    åĩºåıij
    -0.09
    å¥ĭæĸĹ缮æłĩ
    -0.08
    tog
    -0.08
    asia
    -0.08
    åľŃ
    -0.08
    ICS
    -0.08
    дел
    -0.08
    POSITIVE LOGITS
    esy
    0.10
    å¼ĢæĿ¥
    0.10
    ä¸»åľº
    0.10
    åĩŃ
    0.10
    æĨij
    0.10
    åħ¬å¼Ģ课
    0.09
    å®Į好
    0.09
    主æĿĥ
    0.09
    ä¸Ģçķª
    0.09
    ç§ijæķĻ
    0.09
    Activations Density 0.009%

    No Known Activations