© 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. 16827
    Prev
    Next
    INDEX
    Explanations

    so, then

    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
     unpaid
    -0.09
    åĪĨæĺİ
    -0.08
    ACP
    -0.08
    èĥ½ä¸įèĥ½
    -0.08
     Cater
    -0.08
    engl
    -0.08
    éļ¾éģĵ
    -0.08
    enberg
    -0.07
     numer
    -0.07
    æĹłè®ºå¦Ĥä½ķ
    -0.07
    POSITIVE LOGITS
    ä¸įåĥı
    0.14
    å¾ĹçĽĬäºİ
    0.13
    ä¸İåIJ¦
    0.12
    ä½Ĩä¹Ł
    0.11
     unlike
    0.10
    èī¯å¥½çļĦ
    0.10
    çļĦåīįæıIJä¸ĭ
    0.10
    ä¸įåŃĺåľ¨
    0.10
    ä½Ĩå¦Ĥæŀľ
    0.10
    è¿Ļä¸ĢçĤ¹
    0.10
    Activations Density 0.347%

    No Known Activations