© 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. 605
    Prev
    Next
    INDEX
    Explanations

    energy and metabolism

    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
     pun
    -0.09
    èĤ¤
    -0.09
    èĤ©èĨĢ
    -0.09
     Dio
    -0.09
    .metro
    -0.09
    çĹĽ
    -0.09
     {{↵
    -0.08
    reading
    -0.08
    欣èµı
    -0.08
    强
    -0.08
    POSITIVE LOGITS
     COPYING
    0.10
    綾
    0.10
    èĮħ
    0.09
    é¥®é£Ł
    0.09
    æĿ¡ä¾ĭ
    0.09
    æĩĭ
    0.09
    å¼Ĥåľ°
    0.09
    _ARGUMENT
    0.09
    å¸ľ
    0.08
    åľ°éģĵ
    0.08
    Activations Density 0.051%

    No Known Activations