© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23072
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    æİĩ
    -0.09
     arsch
    -0.09
    人æ°ijæľįåĬ¡
    -0.09
    пал
    -0.09
    argins
    -0.09
    æŃ¹
    -0.08
    æĥ®
    -0.08
    äºĭå®ľ
    -0.08
    åĩĢåĢ¼
    -0.08
    Äħż
    -0.08
    POSITIVE LOGITS
    éĤ£åıª
    0.08
     a
    0.08
     surprise
    0.08
    ä¹Łåıªèĥ½
    0.08
    uso
    0.07
    éģįå¸ĥ
    0.07
    æĻ®éĢļè¯Ŀ
    0.07
    åįģ足
    0.07
    çīĪæĿĥ声æĺİ
    0.07
     an
    0.07
    Activations Density 0.139%

    No Known Activations