© 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. 16763
    Prev
    Next
    INDEX
    Explanations

    after investigation

    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
    æĶ¾åģĩ
    -0.09
    erves
    -0.09
    é«ĺçļĦ
    -0.09
     Ling
    -0.09
    Setter
    -0.08
    çŃīåĢĻ
    -0.08
    æĦļ
    -0.08
    è¦ģçŁ¥éģĵ
    -0.08
    ç¾İçļĦ
    -0.08
    æĶ¾å¼Ģ
    -0.08
    POSITIVE LOGITS
    åĬłä»¥
    0.10
    è¿ĩåIJİ
    0.09
    åĬªåĬĽ
    0.09
    管çIJĨæĿ¡ä¾ĭ
    0.09
    æ¥ŀ
    0.09
    ampo
    0.09
    åĬª
    0.09
    ascript
    0.09
    è¿Ļæī¹
    0.09
    å®ĿçŁ³
    0.09
    Activations Density 0.117%

    No Known Activations