© 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. 12365
    Prev
    Next
    INDEX
    Explanations

    body and mind

    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
    æĬł
    -0.08
    çļĦ人çī©
    -0.08
    askan
    -0.08
    åĽĬ
    -0.08
    åĪĨ解
    -0.08
    讲究
    -0.08
    çıŃ
    -0.08
     Decom
    -0.08
    vez
    -0.08
    æij©æĵ¦
    -0.08
    POSITIVE LOGITS
    à¸ģาย
    0.13
    躯
    0.12
    çļĦ身ä½ĵ
    0.12
    身é«Ķ
    0.12
    身ä½ĵ
    0.11
    å¿ĥçģµ
    0.11
    ç²¾ç¥ŀ
    0.11
    身å¿ĥ
    0.10
    å¯Ŀ室
    0.10
     Minds
    0.10
    Activations Density 0.065%

    No Known Activations