© 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. 22489
    Prev
    Next
    INDEX
    Explanations

    Obamacare exchange website

    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
    顺
    -0.09
    èĤ²äºº
    -0.09
    çİĦ
    -0.09
     gaz
    -0.09
    åħĥ
    -0.09
     conservatism
    -0.09
    ä¸ĭä¸Ģç¯ĩ
    -0.08
    ä¸Ī夫
    -0.08
    heads
    -0.08
    æ´ĭ
    -0.08
    POSITIVE LOGITS
    оÑĤов
    0.10
    åľºåIJĪ
    0.10
     Obamacare
    0.10
    asu
    0.09
    å¾Ĺ好
    0.09
    鸳
    0.09
     ÑĢей
    0.09
    å¾ģæĶ¶
    0.09
    åĮ»çĸĹæľįåĬ¡
    0.09
    寿
    0.09
    Activations Density 0.141%

    No Known Activations