© 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. 26050
    Prev
    Next
    INDEX
    Explanations

    news and tragic events

    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
    æĴ¥
    -0.10
    æ´Ĺæīĭ
    -0.10
     Gamb
    -0.09
    æĭ¨
    -0.09
    çļ´
    -0.09
    eness
    -0.09
     dafür
    -0.09
    append
    -0.09
    å±Ļ
    -0.09
    asl
    -0.08
    POSITIVE LOGITS
    好æ¶Īæģ¯
    0.25
     news
    0.22
    news
    0.19
    ãĥĭãĥ¥ãĥ¼ãĤ¹
    0.18
    æ¶Īæģ¯
    0.18
    æĸ°éĹ»
    0.17
     News
    0.17
     новоÑģÑĤи
    0.17
    çļĦæ¶Īæģ¯
    0.17
    News
    0.16
    Activations Density 0.085%

    No Known Activations