© 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. 63765
    Prev
    Next
    INDEX
    Explanations

    from contributions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èľī
    -0.10
    ä¸ĢæĹı
    -0.10
    å®£ä¼łæ´»åĬ¨
    -0.09
    æĢĽ
    -0.09
    å°ļ
    -0.09
     Clair
    -0.08
     Jag
    -0.08
    æķĸ
    -0.08
    ä¹Łåı¯èĥ½
    -0.08
     Jin
    -0.08
    POSITIVE LOGITS
    æĿ¥èĩª
    0.20
    ä¾Ĩèĩª
    0.17
    æĿ¥èĩªäºİ
    0.15
     contributions
    0.13
     from
    0.13
     contribution
    0.11
    æĺ¯çĶ±
    0.10
     ÙħÙĨÙĩÙħ
    0.10
    åĩºèĩª
    0.10
     från
    0.10
    Activations Density 0.161%

    No Known Activations