© 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. 696
    Prev
    Next
    INDEX
    Explanations

    rinsing, flushing outlet, Copyright

    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
    é«»
    -0.10
    rian
    -0.10
    mente
    -0.10
    å¤§éĽ¨
    -0.10
    ä¸ĢåĽ¢
    -0.10
    aceous
    -0.09
    æĬ¤èº«
    -0.09
    èĵ¬
    -0.09
    /big
    -0.09
    ereal
    -0.09
    POSITIVE LOGITS
    OrCreate
    0.10
    æ¼ĵ
    0.09
    æİī
    0.09
    æİīäºĨ
    0.09
    bred
    0.09
    ott
    0.08
    ä¼Ĭæĸ¯
    0.08
    otte
    0.08
    MORE
    0.08
    åĪ«è¯´
    0.08
    Activations Density 0.006%

    No Known Activations