© 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. 3012
    Prev
    Next
    INDEX
    Explanations

    possessive 's followed by articles

    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
    -même
    -0.09
    ะ
    -0.08
    ein
    -0.08
     counter
    -0.08
    éĿŀ常åĸľæ¬¢
    -0.08
     sina
    -0.08
    ÑģÑĤавлен
    -0.07
    æĺİæľĹ
    -0.07
    èĥľ
    -0.07
    ÙĬÙĩ
    -0.07
    POSITIVE LOGITS
    éĺ´è°ĭ
    0.09
    çİ¢
    0.09
    该éĻ¢
    0.09
    åıĪ好
    0.09
    åĮħ裹
    0.09
    åīĶ
    0.09
    åĢ¼å¾Ĺä¸Ģ
    0.09
    æ¹ĺ西
    0.09
    ystem
    0.09
    æľĢéĢĤåIJĪ
    0.09
    Activations Density 0.025%

    No Known Activations