© 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. 60562
    Prev
    Next
    INDEX
    Explanations

    cooking instructions or recipe steps

    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
    对ä»ĸ们
    -0.11
     Lay
    -0.10
    åĨ»
    -0.10
    LAY
    -0.10
     hÆ°á»Łng
    -0.09
    .overlay
    -0.09
     Sandwich
    -0.09
    æīĺ
    -0.09
     Gree
    -0.09
    .spi
    -0.09
    POSITIVE LOGITS
    沸èħ¾
    0.11
    诰
    0.10
    鸱
    0.10
    沸
    0.09
    鸳
    0.09
    竽
    0.09
    泡泡
    0.09
    æ°´éĿ¢
    0.09
     Hank
    0.08
    åħļåijĺå¹²éĥ¨
    0.08
    Activations Density 0.026%

    No Known Activations