© 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. 6170
    Prev
    Next
    INDEX
    Explanations

    clarity

    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
    çݰ象
    -0.09
    ä¿ļ
    -0.09
    å°ıäºĭ
    -0.08
     Sadd
    -0.08
    çİ°æľīçļĦ
    -0.08
    çİ°å®ŀä¸Ń
    -0.08
    _stand
    -0.08
     Transcript
    -0.08
    å¸ĤåľºåĮĸ
    -0.08
    entar
    -0.07
    POSITIVE LOGITS
    è§ĦåĪĴ
    0.12
    å®ı大
    0.11
    æ¸ħæĻ°
    0.11
    æĤ
    0.10
    æ¸ħæ¥ļ
    0.09
    å¦ĤæĦı
    0.09
    æĵĺ
    0.09
    æĮĩå¼ķ
    0.09
    è¿ľæĻ¯
    0.09
     clarity
    0.09
    Activations Density 0.141%

    No Known Activations