© 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. 16601
    Prev
    Next
    INDEX
    Explanations

    through the

    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
    å®ŀéĻħæĥħåĨµ
    -0.10
    æĸĹ
    -0.09
     ÑģÑĦ
    -0.09
     Hass
    -0.09
    åIJĦ个æĸ¹éĿ¢
    -0.09
    åIJĮåŁİ
    -0.09
    åºĶæľīçļĦ
    -0.09
    åºĶåıĬæŶ
    -0.09
    å°ĸ
    -0.08
    å¥ĭæĸĹ缮æłĩ
    -0.08
    POSITIVE LOGITS
    amic
    0.09
    çİĭåŃIJ
    0.08
    以åĨħ
    0.08
    جÙĬ
    0.08
    alis
    0.08
    åijĬ
    0.08
    人人
    0.08
    atchet
    0.08
    èµĸ以
    0.08
     sieve
    0.08
    Activations Density 0.088%

    No Known Activations