© 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. 26119
    Prev
    Next
    INDEX
    Explanations

    possessive noun endings

    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
    åľ¨åIJĮä¸Ģ
    -0.09
    å¦Ī
    -0.09
    éĽĨè£ħ
    -0.09
    è´µ
    -0.08
     ÑģÑĤоим
    -0.08
     freder
    -0.08
    家æĹı
    -0.08
    æĿµ
    -0.08
    èݲèĬ±
    -0.07
    ä½ĽéĻĢ
    -0.07
    POSITIVE LOGITS
    åIJĦ级
    0.11
    帮ä»ĸ
    0.11
    oba
    0.10
    æ¶Įçİ°åĩº
    0.09
    æīĢæľīçļĦ
    0.09
    åIJĦå¼ı
    0.09
    ä»Ģä¹Īåľ°æĸ¹
    0.09
    ç§ijçłĶéĻ¢æīĢ
    0.09
    ouse
    0.09
    大å°ı
    0.09
    Activations Density 0.071%

    No Known Activations