© 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. 9313
    Prev
    Next
    INDEX
    Explanations

    morbidity and mortality

    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éĩıçļĦ
    -0.10
    æĬĢæľ¯äººåijĺ
    -0.09
    æīĭå·¥
    -0.09
    話
    -0.09
    ãģĥ
    -0.09
    人éĥ½
    -0.08
    ç¾İ好
    -0.08
    æ´»å¾Ĺ
    -0.08
    管å§Ķä¼ļ
    -0.08
    odiac
    -0.08
    POSITIVE LOGITS
    cheid
    0.10
    inning
    0.09
    åĩĿ
    0.09
    ctrl
    0.08
    çĶļèĩ³è¿ŀ
    0.08
    aban
    0.08
    é£İçŃĿ
    0.08
    ugs
    0.08
    >Delete
    0.07
    oner
    0.07
    Activations Density 2.148%

    No Known Activations