© 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. 47592
    Prev
    Next
    INDEX
    Explanations

    putting in or get in

    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
    æļĩ
    -0.10
    主æĦı
    -0.09
     Crash
    -0.09
     limp
    -0.09
    大éĿ¢ç§¯
    -0.09
    çģ«çĤ¬
    -0.08
    éģ½
    -0.08
    thesis
    -0.08
    æ³ķåѦ
    -0.08
    afen
    -0.08
    POSITIVE LOGITS
    çݰ代社ä¼ļ
    0.09
    é³Į
    0.09
    楸
    0.08
    æľ
    0.08
    å½¢æĪIJäºĨ
    0.08
    æĺİ
    0.08
     обÑĢаÑī
    0.08
    _delegate
    0.08
    åıĮçľ¼
    0.08
    odb
    0.08
    Activations Density 0.047%

    No Known Activations