© 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. 40348
    Prev
    Next
    INDEX
    Explanations

    activities ending in activities

    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
    æİ¥æīĭ
    -0.09
    éĺİ
    -0.09
    绣é¢Ĩ
    -0.09
     Balk
    -0.09
    製
    -0.09
    人éĻħ
    -0.09
    eer
    -0.09
    æĥ®
    -0.08
    ï¸ı
    -0.08
     kü
    -0.08
    POSITIVE LOGITS
     Mans
    0.09
    åıijè´¢
    0.08
    æĦıæĦ¿
    0.08
    &E
    0.08
    åĪĹ为
    0.08
    çīĩåŃIJ
    0.08
    sock
    0.08
     sou
    0.08
    WARE
    0.08
    éĥijéĩį
    0.08
    Activations Density 0.074%

    No Known Activations