© 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. 16537
    Prev
    Next
    INDEX
    Explanations

    every single

    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
    æľ¬èº«çļĦ
    -0.11
    åĶ¯ä¸ĢçļĦ
    -0.10
    好çİ©
    -0.09
    åĩºè·¯
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    æľ¬èº«
    -0.09
    笳
    -0.09
    èĩªèº«çļĦ
    -0.09
    spe
    -0.09
    allee
    -0.08
    POSITIVE LOGITS
    éĢIJä¸Ģ
    0.17
    æĬĬè¿ĻäºĽ
    0.16
    ä¸Ģä¸Ģ
    0.16
    è¿ĻäºĽ
    0.15
    è¿Ļåĩłä¸ª
    0.14
    ä¸Ĭè¿°
    0.13
    ãģĵãĤĮãĤīãģ®
    0.13
    éĢIJ
    0.13
    è¿ĻäºĽéĹ®é¢ĺ
    0.13
    è¿Ļä¸ī个
    0.13
    Activations Density 0.206%

    No Known Activations