© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 804
    Prev
    Next
    INDEX
    Explanations

    formed or forming something

    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
    Negative Logits
    鼷
    -0.08
     hem
    -0.08
    对æĸ¹
    -0.08
    æĤ¨çļĦåŃ©åŃIJ
    -0.08
     Dwight
    -0.08
    ä¸įä¸Ĭ
    -0.08
    ë³´ê³ł
    -0.08
     Cups
    -0.08
    è¡Įç¨ĭ
    -0.08
    dit
    -0.07
    POSITIVE LOGITS
    æĪIJç«ĭäºĨ
    0.17
    æĪIJç«ĭ
    0.17
    注åĨĮèµĦæľ¬
    0.09
    çIJħ
    0.09
    ä¹ĭåĪĿ
    0.09
     комиÑģÑģи
    0.09
    æĪIJç«ĭäºİ
    0.09
    ä¸ĢæĶ¯
    0.09
    è§Ĥå½±
    0.09
    phin
    0.08
    Activations Density 0.020%

    No Known Activations