© 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. 24002
    Prev
    Next
    INDEX
    Explanations

    $_[' heading_title

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĸĩä½ĵ
    -0.09
    å¸ĮæľĽèĥ½
    -0.09
    饷
    -0.08
    æĪIJ绩åįķ
    -0.08
    URN
    -0.08
    åŀŃ
    -0.08
    æ²Ļæ¼ł
    -0.08
    å¤©åºľ
    -0.08
    çīĮ
    -0.08
    åºķ
    -0.08
    POSITIVE LOGITS
    æī¿
    0.10
    èĩªæĿ¥
    0.10
    èĹķ
    0.10
    aks
    0.09
    æ´¾éģ£
    0.09
    ulta
    0.08
    åľ¨æł¡
    0.08
    istle
    0.08
    æ¸ħåĩī
    0.08
    Vendor
    0.08
    Activations Density 0.017%

    No Known Activations