© 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. 56584
    Prev
    Next
    INDEX
    Explanations

    often innovative

    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
    æī¹åĩĨ
    -0.10
    ä¸Ģ个好çļĦ
    -0.09
     Dedicated
    -0.09
    æĿµ
    -0.09
    æĺ¯ä¸Ģ款
    -0.09
    åĢ¼çıŃ
    -0.09
    æł·æĿ¿
    -0.09
    æľºåĬ¨
    -0.08
    ä¼ĺè¶Ĭ
    -0.08
    è§ļ
    -0.08
    POSITIVE LOGITS
    å¾Ģå¾Ģ
    0.11
    ergic
    0.10
    ä»ĸçļĦ
    0.10
     often
    0.09
    å¾Ģå¾Ģæĺ¯
    0.09
    åĴĮä»ĸçļĦ
    0.09
    äºĨä»ĸçļĦ
    0.09
    æľīæŶ
    0.09
    åľ¨ä»ĸçļĦ
    0.09
    触åıĬ
    0.09
    Activations Density 0.132%

    No Known Activations