© 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. 12408
    Prev
    Next
    INDEX
    Explanations

    numbers and dates, or common prefixes

    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
    æѤ类
    -0.12
    ä¸İåIJ¦
    -0.11
    åĩºå¤Ħ
    -0.08
    è¿ĻäºĽ
    -0.08
    æŁIJæŁIJ
    -0.08
    ertext
    -0.08
    è¿Ļç±»
    -0.07
    åŃ°
    -0.07
    åħ¶ä»ĸ
    -0.07
    åij¼å£°
    -0.07
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.10
    åIJĦ个çݯèĬĤ
    0.10
    åħŃ大
    0.10
    主è¦ģåĮħæĭ¬
    0.10
    åĽĽä¸ªæĸ¹éĿ¢
    0.10
    æĬĢæľ¯åĴĮ
    0.09
    åĽ´ç»ķ
    0.09
    æĺ¯å¦Ĥä½ķ
    0.09
    åįģ大
    0.09
    讲究
    0.09
    Activations Density 1.024%

    No Known Activations