© 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. 47486
    Prev
    Next
    INDEX
    Explanations

    bodybuilding, bulking, body hypertrophy

    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
    _mime
    -0.10
    æ±¾
    -0.10
    å¤§éĽ¨
    -0.09
    irtual
    -0.09
    åľ°éĿ¢
    -0.09
    ected
    -0.09
    _PADDING
    -0.09
    ç®Ģ
    -0.09
    åķ®
    -0.09
    çĥŁåĽ±
    -0.09
    POSITIVE LOGITS
    åģ¥èº«
    0.11
    èĨĬ
    0.10
    å¡ijéĢł
    0.09
    æī£
    0.09
    èĻİ
    0.09
    èĵĦ
    0.09
    åıĶ
    0.09
    è±¹
    0.08
    éĥĹ
    0.08
     fitness
    0.08
    Activations Density 0.118%

    No Known Activations