© 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. 26127
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns

    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
    itor
    -0.09
    åºŀ
    -0.08
    inders
    -0.08
    èĪĤ
    -0.08
    é¢ĦåijĬ
    -0.08
    èĩªæľī
    -0.08
    oller
    -0.08
     donated
    -0.07
    è²´
    -0.07
    iers
    -0.07
    POSITIVE LOGITS
    é¢ľ
    0.10
    èħ´
    0.10
     Newly
    0.10
    itol
    0.09
     lạc
    0.09
    åľ¨æł¡
    0.09
    æĿĥåĪ©
    0.09
     má»ĩnh
    0.09
    uur
    0.09
    ç»ıå¼Ģ
    0.09
    Activations Density 0.022%

    No Known Activations