© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58192
    Prev
    Next
    INDEX
    Explanations

    health care provision issues

    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
    ä¸ĭå±ŀ
    -0.09
    æ¡ĥ
    -0.08
    efs
    -0.08
    人工
    -0.08
    IMIT
    -0.07
    ENOMEM
    -0.07
    ä»»ä½ķå½¢å¼ı
    -0.07
     EN
    -0.07
    cks
    -0.07
    UMAN
    -0.07
    POSITIVE LOGITS
    ä¸ĵéĹ¨ä¸º
    0.23
    éĴĪ对æĢ§
    0.18
    éĴĪ对
    0.17
    ä¸ĵéŨ
    0.17
    æĽ´éĢĤåIJĪ
    0.16
    éĩĿå°į
    0.15
    æľīéĴĪ对æĢ§
    0.15
    对ä»ĸ们
    0.14
    éĿŀ常éĢĤåIJĪ
    0.14
    çī¹æĦı
    0.14
    Activations Density 0.299%

    No Known Activations