© 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. 36619
    Prev
    Next
    INDEX
    Explanations

    picture of a

    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
    è°ģçŁ¥éģĵ
    -0.09
    ç»ĻåŃ©åŃIJ
    -0.09
    åľ¨æĹ¥æľ¬
    -0.09
    带ä¸Ĭ
    -0.09
    æµĶ
    -0.09
    каÑĤ
    -0.08
     ç»ĵ
    -0.08
    é¡¿
    -0.08
    aurus
    -0.08
    æ¶ĪåĮĸ
    -0.08
    POSITIVE LOGITS
     images
    0.10
     pictures
    0.10
    çĶ»éĿ¢
    0.10
    çļĦçĶ»éĿ¢
    0.10
    çħ§çīĩ
    0.09
    à¸łà¸²à¸ŀ
    0.09
    æĻ¯è±¡
    0.09
    çīĪæĿĥ声æĺİ
    0.09
     chụp
    0.09
    è¿İ
    0.08
    Activations Density 0.110%

    No Known Activations