© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5239
    Prev
    Next
    INDEX
    Explanations

    food and drink

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ©é¤IJ
    -0.11
    仪
    -0.10
    åįĪé¤IJ
    -0.09
    é£Łåĵģ
    -0.09
     food
    -0.09
     Diet
    -0.09
     aliment
    -0.08
     foods
    -0.08
    é£Łçī©
    -0.08
    鹤
    -0.08
    POSITIVE LOGITS
    ä¸įå®Į
    0.10
    çĶŃ
    0.09
    ä¼ijæģ¯
    0.09
     nas
    0.09
    enco
    0.08
    è¹
    0.08
    ä½ı宿
    0.08
    娱ä¹IJ
    0.08
    ä¸įåı¯éģ¿åħį
    0.08
    åIJ¹
    0.08
    Activations Density 0.070%

    No Known Activations