© 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. 26322
    Prev
    Next
    INDEX
    Explanations

    tech stack technologies

    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
    佯
    -0.10
    WithContext
    -0.10
    衾
    -0.09
    æ¼ķ
    -0.09
    山寨
    -0.09
    unts
    -0.08
     youre
    -0.08
    èĩ¨
    -0.08
    ä¸İåħ¶ä»ĸ
    -0.08
    å©ī
    -0.08
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.11
     technologies
    0.11
    æłĪ
    0.10
    fos
    0.09
     ÑĤеÑħнологии
    0.09
    perl
    0.09
    âĸĬ
    0.09
    _rest
    0.09
    æľĢåħĪè¿ĽçļĦ
    0.09
     front
    0.09
    Activations Density 0.233%

    No Known Activations