© 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. 12291
    Prev
    Next
    INDEX
    Explanations

    pumped up, protect, sets, reps

    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
    ä¸ĢåŃĹ
    -0.10
    è·³
    -0.10
    -launch
    -0.10
    æŃ¡è¿İ
    -0.10
    对ä»ĸ们
    -0.10
    è´¨æ£Ģ
    -0.09
    èĨĿçĽĸ
    -0.09
    çłº
    -0.09
    èĭ¦
    -0.09
    (weights
    -0.09
    POSITIVE LOGITS
     Infer
    0.10
    æĶ¶èİ·
    0.09
    çĶµä¿¡
    0.08
     ink
    0.08
    æĸ°æ¨¡å¼ı
    0.08
    ink
    0.08
    å´Ń
    0.08
    人æµģ
    0.08
    olan
    0.08
     mA
    0.08
    Activations Density 0.039%

    No Known Activations