© 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. 47495
    Prev
    Next
    INDEX
    Explanations

    system requirements version

    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
    æĺİæĺİ
    -0.08
    å§
    -0.08
     buck
    -0.08
    æīĭæľºçīĪ
    -0.08
    å½
    -0.08
    itto
    -0.08
    tim
    -0.08
     ká»ĭp
    -0.08
    puty
    -0.08
    blockquote
    -0.07
    POSITIVE LOGITS
    æľĢä½İ
    0.17
    ä¸įä½İäºİ
    0.15
    èĩ³å°ij
    0.14
    æľĢå°ij
    0.14
     minimum
    0.12
    èµ·çłģ
    0.12
    ä¸įå°ijäºİ
    0.12
     mÃŃnimo
    0.11
    Minimum
    0.11
    minimum
    0.11
    Activations Density 0.045%

    No Known Activations