© 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. 12274
    Prev
    Next
    INDEX
    Explanations

    method proposed

    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
    ä¸İä¼Ĺ
    -0.10
    amb
    -0.09
    骨æŀ¶
    -0.09
    ä¸į失
    -0.08
    æŨ
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    éĢļçŁ¥ä¹¦
    -0.08
    artisan
    -0.08
    诡
    -0.08
    桧
    -0.08
    POSITIVE LOGITS
    说è¿ĩ
    0.16
    æľī人说
    0.15
    说æĺ¯
    0.15
    建议
    0.14
    æıIJåĩºçļĦ
    0.11
    æıIJåĩº
    0.11
    说æ³ķ
    0.11
    建èŃ°
    0.11
    æıIJè®®
    0.11
     suggestion
    0.11
    Activations Density 0.258%

    No Known Activations