© 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. 40190
    Prev
    Next
    INDEX
    Explanations

    great way

    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
    ä¸įæĩĪ
    -0.10
     rang
    -0.09
    åĸĨ
    -0.09
    çļĦæĸĩç«ł
    -0.09
    çķı
    -0.08
    rang
    -0.08
    æĸĩç«ł
    -0.08
    æĶ¾åĪ°
    -0.08
    ä¸Ģä¸Ŀ
    -0.08
    åŁºæķ°
    -0.08
    POSITIVE LOGITS
     way
    0.13
    çļĦæĸ¹å¼ı
    0.12
     ways
    0.12
    çļĦæĸ¹å¼ıæĿ¥
    0.12
     ÑģпоÑģоб
    0.11
    æµģè¡Į
    0.10
    æįŀ
    0.10
    inance
    0.09
    .setFill
    0.09
    æľīæķĪçļĦ
    0.09
    Activations Density 0.071%

    No Known Activations