© 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. 47413
    Prev
    Next
    INDEX
    Explanations

    milk fat percentage

    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¸ĢæĹ¥
    -0.10
    è¿ľæĸ¹
    -0.10
    说åĩºæĿ¥
    -0.09
    å§Ĭ妹
    -0.08
    oen
    -0.08
    æ·±åħ¥äºĨ解
    -0.08
    ä¸Ģ天
    -0.08
    _vk
    -0.08
    ä¸ĭ乡
    -0.08
     damn
    -0.08
    POSITIVE LOGITS
    èĦĤèĤª
    0.09
    cream
    0.09
    èľľ
    0.08
    è´¢æĶ¿
    0.08
    LOAT
    0.08
     dairy
    0.08
     satin
    0.08
    èĤª
    0.08
    UTIL
    0.08
    ucch
    0.08
    Activations Density 0.063%

    No Known Activations