© 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. 791
    Prev
    Next
    INDEX
    Explanations

    complacency, relaxation, let down guard

    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
    éģ¿å¼Ģ
    -0.10
    çĽĬ
    -0.10
    à¹Ģà¸Ĺศ
    -0.09
    ãģ¨ãģĦãģĪãģ°
    -0.09
    毡
    -0.09
    æĹłå¥Ī
    -0.09
    èĦı
    -0.09
    å¢ŀèĩ³
    -0.09
     пÑĢеимÑĥÑīеÑģÑĤв
    -0.09
    話
    -0.09
    POSITIVE LOGITS
    æĩĪ
    0.21
    æĶ¾æĿ¾
    0.20
    麻çĹ¹
    0.17
    æĢł
    0.14
     compl
    0.13
     relaxing
    0.13
    çĸı
    0.12
     Relax
    0.12
    侥幸
    0.12
     relax
    0.11
    Activations Density 0.048%

    No Known Activations