© 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. 47733
    Prev
    Next
    INDEX
    Explanations

    learned, know, covered, lesson

    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
     CVS
    -0.08
    qv
    -0.08
    ening
    -0.08
    ä¸įä½İäºİ
    -0.08
    hausen
    -0.08
    ä¸įå®ļ
    -0.08
     Fam
    -0.08
    rary
    -0.08
    èĩĤ
    -0.08
    æľĢåIJİä¸Ģ次
    -0.08
    POSITIVE LOGITS
    æīįçŁ¥éģĵ
    0.12
    äºĨ许å¤ļ
    0.11
    许å¤ļ
    0.11
     myself
    0.10
    æ·±åĪ»çļĦ
    0.10
    äºĨ好å¤ļ
    0.10
    ä»Ģä¹Īåı«
    0.10
    æĽ´åĬł
    0.10
    æĺİçĻ½äºĨ
    0.10
    äºĨå¾Īå¤ļ
    0.10
    Activations Density 0.074%

    No Known Activations