© 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. 63960
    Prev
    Next
    INDEX
    Explanations

    system performance 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
    Negative Logits
    跨度
    -0.10
    è¿¢
    -0.09
    æĸ¹ä½į
    -0.09
    æłĩåĩĨåĮĸ
    -0.09
    (parts
    -0.09
     ÑģÑĤо
    -0.09
    /antlr
    -0.09
    chai
    -0.09
    è®°è½½
    -0.09
     UNU
    -0.08
    POSITIVE LOGITS
    饥饿
    0.10
    _CPU
    0.09
    åĨ¤
    0.09
    é¢ijé¢ij
    0.09
    CPU
    0.09
    ä¸įåłª
    0.08
    京åŁİ
    0.08
    è°ĥ度
    0.08
    åij½ä¸Ń
    0.08
     tuned
    0.08
    Activations Density 0.297%

    No Known Activations