© 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. 6284
    Prev
    Next
    INDEX
    Explanations

    connected to

    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
    ern
    -0.09
    åĽłèĢĮ
    -0.08
    ä¸Ģç«Ļå¼ı
    -0.08
    çijĽ
    -0.08
    äººåľ¨
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    æ©Ħæ¦Ħ
    -0.08
    人çĶŁçļĦ
    -0.08
    éĤ£ç§į
    -0.08
    ç©¿ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    NESS
    0.09
    ims
    0.09
    pler
    0.09
    äºĨå¤ļå°ij
    0.09
    ately
    0.09
    äºĨä¸įå°ij
    0.09
    æĿ¯åŃIJ
    0.09
    å³Ļ
    0.09
    äºĨ许å¤ļ
    0.09
    etter
    0.09
    Activations Density 0.726%

    No Known Activations