© 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. 16696
    Prev
    Next
    INDEX
    Explanations

    possessive proper nouns

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.10
    ä¸Ģæī¹
    -0.10
    身边çļĦ
    -0.09
    ä½ĵåĨħ
    -0.09
    åĴĮæľįåĬ¡
    -0.09
    æĭ¦æĪª
    -0.09
    çľĭä¸įåĪ°
    -0.09
    为æĬĵæīĭ
    -0.09
    äºĨä¸Ģæī¹
    -0.08
    çĶŁæ´»åľ¨
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.19
     overall
    0.15
    Overall
    0.14
    çļĦæķ´ä½ĵ
    0.13
    æĢ»çļĦæĿ¥è¯´
    0.13
    åħ¶å®ĥ
    0.13
    æľ¬èº«
    0.12
    åħ¶ä»ĸ
    0.12
     itself
    0.12
    æĢ»ä½ĵ
    0.11
    Activations Density 0.332%

    No Known Activations