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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20883
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    ä¾£
    -0.10
    ä¿IJ
    -0.10
    ä¸įä½Ĩ
    -0.10
    åĶī
    -0.09
    说ä¸įå®ļ
    -0.09
    èµĦæºIJéħįç½®
    -0.09
    å«Ĥ
    -0.09
    好åIJĹ
    -0.09
    åħ¶å®ŀæĺ¯
    -0.09
    纶
    -0.08
    POSITIVE LOGITS
    æĪijä»¬åľ¨
    0.09
    æĪijä»¬çŁ¥éģĵ
    0.09
    éĹ®éĹ®
    0.09
     ÑģаÑħ
    0.08
    æĪijä»¬ä¹Ł
    0.08
     (?)
    0.08
    è¦ģæĬĬ
    0.08
    ĽĦ
    0.08
    ãģªãģĮãĤī
    0.08
    gemÃ¤ÃŁ
    0.08
    Activations Density 0.005%

    No Known Activations