© 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. 60624
    Prev
    Next
    INDEX
    Explanations

    pictured / photo / Dust

    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
    èĢģ乡
    -0.11
    ä»Ģä¹Īåij¢
    -0.10
    obe
    -0.10
    å¾Īéķ¿
    -0.10
    娩
    -0.09
    åĪļéľĢ
    -0.09
    åģŃ
    -0.09
    è¿ĺ羣
    -0.09
    åIJĦæł·
    -0.09
     móc
    -0.09
    POSITIVE LOGITS
    ä¾ĽåĽ¾
    0.10
    è¿ĻéĩĮæĺ¯
    0.09
     pictured
    0.08
    è¿Ļä¸ĢåĪ»
    0.08
    (Photo
    0.08
    æѤå¤Ħ
    0.08
    Photo
    0.08
    æ´»åĬ¨çİ°åľº
    0.08
     Dust
    0.07
    æİ¥åıĹéĩĩ访
    0.07
    Activations Density 0.307%

    No Known Activations