© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62329
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or conjunctions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ľä¸ºä¸Ģ个
    -0.10
    æĪij们éĥ½
    -0.10
    æĪIJ为ä¸ĢåIJį
    -0.09
    大家éĥ½
    -0.09
    ://%
    -0.09
    éģŃåĪ°
    -0.09
    ä½ľä¸ºä¸ĢåIJį
    -0.09
    家ä½ı
    -0.09
    好æľĭåıĭ
    -0.09
    åľ¨æİ¥åıĹ
    -0.09
    POSITIVE LOGITS
     themselves
    0.17
     Ñģами
    0.11
    ä»ĸ们çļĦ
    0.11
     thems
    0.10
    ä»ĸ们
    0.10
    åħ±è¯Ĩ
    0.09
    ä»ĸä»¬åľ¨
    0.09
    ä½Ĩä»ĸ们
    0.09
    åIJĦèĩª
    0.09
    åĽłä¸ºä»ĸ们
    0.09
    Activations Density 0.109%

    No Known Activations