© 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. 47543
    Prev
    Next
    INDEX
    Explanations

    spicy food and taste

    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
    èĽĢ
    -0.11
    çĩİ
    -0.10
    ç§Ń
    -0.09
    uze
    -0.09
    积æŀģåĵįåºĶ
    -0.09
    çªĸ
    -0.09
    åı¯è§ģ
    -0.09
     Congressional
    -0.09
    梧
    -0.09
    ç½®ä¸ļ
    -0.09
    POSITIVE LOGITS
    åĪĿ
    0.09
     rig
    0.09
    æĮijåīĶ
    0.09
    æİĪ
    0.09
    alle
    0.08
     ace
    0.08
    åij³éģĵ
    0.08
    åѤç«ĭ
    0.08
    ALLE
    0.08
    bos
    0.08
    Activations Density 0.055%

    No Known Activations