© 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. 12175
    Prev
    Next
    INDEX
    Explanations

    lactose malabsorption

    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
    们çļĦ
    -0.09
    _mov
    -0.08
    èĤ¯
    -0.08
    鸡èĽĭ
    -0.08
    åįİ
    -0.08
    Destroyed
    -0.08
    æ¦Ĥ
    -0.08
    holes
    -0.07
    ipv
    -0.07
    ç¾¹
    -0.07
    POSITIVE LOGITS
    aminer
    0.10
    åĵº
    0.10
    ÑĪиб
    0.09
    çĤ¹æ»´
    0.09
     Mellon
    0.09
    åķ¤
    0.09
    åĨľçī§
    0.09
     Warriors
    0.09
    éķ¶åµĮ
    0.09
    ä¸ĩåIJį
    0.09
    Activations Density 0.052%

    No Known Activations