© 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. 64089
    Prev
    Next
    INDEX
    Explanations

    revolution, unrest, revival, Renaissance

    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
    è¡Ķ
    -0.10
    æķ´æĶ¹æݪæĸ½
    -0.09
     пÑĢож
    -0.08
    æĸ
    -0.08
    ç¿Ķ
    -0.08
    å®ħ
    -0.08
    ä¸ĬåįĬå¹´
    -0.08
    åĪĴå®ļ
    -0.08
     ald
    -0.08
    irim
    -0.08
    POSITIVE LOGITS
     revolution
    0.10
    欣
    0.10
    ãģ¤ãģ¤
    0.09
    æ®Ĩ
    0.09
    æİĢ
    0.09
    æĿ¥ä¸´
    0.09
    è¿·ä½ł
    0.09
    naissance
    0.09
    幸
    0.09
    浪潮
    0.09
    Activations Density 0.064%

    No Known Activations