© 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. 29456
    Prev
    Next
    INDEX
    Explanations

    describing size and condition

    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
    éªĬ
    -0.10
     jes
    -0.10
    身ä¸Ĭ
    -0.10
    åīįæıIJæĺ¯
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.09
    æĹłè®º
    -0.09
    åĴĮåľ°åĮº
    -0.09
    å±ģ
    -0.09
    TimeInterval
    -0.09
    UCE
    -0.08
    POSITIVE LOGITS
    fully
    0.09
    clearfix
    0.09
     hare
    0.08
    تÙĤ
    0.08
    è³¢
    0.08
     bene
    0.08
    æģĻ
    0.07
    åıijæĮ¥ä½ľçĶ¨
    0.07
     Barr
    0.07
     Aud
    0.07
    Activations Density 0.629%

    No Known Activations