© 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. 12287
    Prev
    Next
    INDEX
    Explanations

    propose or announce

    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
    linger
    -0.09
    æĹłæķ°æ¬¡
    -0.09
    éĿ¢åŃIJ
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.09
    ins
    -0.08
    ongo
    -0.08
    procs
    -0.08
    æ·³
    -0.08
    æľ´å®ŀ
    -0.08
    kip
    -0.07
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.14
     اÙĦÙħزÙĬد
    0.13
    尽快
    0.13
    ä¸ĭä¸ĢæŃ¥
    0.13
    ä¸ĭåij¨
    0.13
    å±ĬæŶ
    0.12
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.12
     forthcoming
    0.12
    æĺİ天
    0.12
    ä¸ĭä¸Ģ个
    0.12
    Activations Density 0.136%

    No Known Activations