© 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. 22320
    Prev
    Next
    INDEX
    Explanations

    ever followed by a verb

    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
    å·²æľī
    -0.09
    å¸Ń
    -0.09
    å·²ç»ıæľī
    -0.09
    æ¯ıä¸Ģ次
    -0.09
     Ø¥ÙĦا
    -0.09
    å¾Ģå¾Ģ
    -0.08
    éĢļ常
    -0.08
    åѵ
    -0.08
    æıŃ
    -0.08
    æ®ĵ
    -0.08
    POSITIVE LOGITS
    æĪIJ为ä¸ŃåĽ½
    0.10
    éļ¾å¿ĺ
    0.09
     Woj
    0.08
    hin
    0.08
    åĵŃ
    0.08
    oe
    0.08
    åį°è±¡
    0.08
    _SWITCH
    0.08
    大è§Ħ模
    0.08
    类似çļĦ
    0.08
    Activations Density 0.008%

    No Known Activations