© 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. 6077
    Prev
    Next
    INDEX
    Explanations

    clothing descriptions

    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
    è¿Ļ家ä¼Ļ
    -0.10
    éļ°
    -0.09
    å°ıå°ı
    -0.09
    éĢĨåĬ¿
    -0.09
    ndef
    -0.09
    çĪ±åĽ½
    -0.09
    æĭ³
    -0.09
    åĽ½äºº
    -0.09
    æ°ijçĶŁ
    -0.09
    è¶Ĭéĩİ
    -0.08
    POSITIVE LOGITS
    å¢ŀèµĦ
    0.10
    maid
    0.09
     VIDEO
    0.09
    èłķ
    0.09
    褶
    0.09
    æģ¯
    0.08
    trap
    0.08
     sequ
    0.08
    å®ļåĪ¶
    0.08
    ieres
    0.08
    Activations Density 0.047%

    No Known Activations