© 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. 59427
    Prev
    Next
    INDEX
    Explanations

    clothing styles and concepts

    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
    pit
    -0.08
    ovel
    -0.07
    пÑĥÑģк
    -0.07
    åħĪéĶĭ
    -0.07
     dee
    -0.07
    --
    -0.07
     contr
    -0.07
    g
    -0.07
     ìĭ
    -0.07
    çĭŃ
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.16
    çļĦåģļæ³ķ
    0.12
    è¿Ļä¹Ł
    0.12
    æĺ¯ä¸Ģ件
    0.11
    å¾Īå¥½åľ°
    0.11
    èĢĥéªĮ
    0.11
    éĩįè¦ģæĦıä¹ī
    0.11
    尤为éĩįè¦ģ
    0.11
    ä¹Łæĺ¯ä¸Ģç§į
    0.11
    çļĦéģĵçIJĨ
    0.11
    Activations Density 0.629%

    No Known Activations