© 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. 29664
    Prev
    Next
    INDEX
    Explanations

    beans and pulses

    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
    ulum
    -0.09
    abled
    -0.09
    von
    -0.08
    åIJĥåĪ°
    -0.08
    ixed
    -0.08
    ä½İ头
    -0.08
    ä¾
    -0.08
    ÑģÑı
    -0.08
    漫
    -0.08
    ä¼İ
    -0.08
    POSITIVE LOGITS
    ä»İä¸Ń
    0.09
    èĶ»
    0.09
    gens
    0.09
     маÑĢÑĪ
    0.08
     Hubb
    0.08
    èĬ½
    0.08
    æ¼Ĩ
    0.08
     Wagner
    0.08
    å¹ķå¢Ļ
    0.08
    beans
    0.08
    Activations Density 0.011%

    No Known Activations