© 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. 6160
    Prev
    Next
    INDEX
    Explanations

    personally

    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
    ç»Ĩèħ»
    -0.11
    ÑİÑĢ
    -0.10
    åĪ°åºķ
    -0.09
    åijĬè¯īä½ł
    -0.09
    åĪ°åºķæĺ¯
    -0.09
    大家éĥ½åľ¨
    -0.09
    å¨ĺ
    -0.09
    妹
    -0.09
    æĺĶæĹ¥
    -0.09
    ixo
    -0.09
    POSITIVE LOGITS
    agen
    0.10
     pres
    0.08
    æªIJ
    0.08
     already
    0.08
    agem
    0.08
    geh
    0.08
    cran
    0.08
     RC
    0.08
    ä»ĸå·²ç»ı
    0.08
    agens
    0.08
    Activations Density 0.024%

    No Known Activations