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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20882
    Prev
    Next
    INDEX
    Explanations

    crops and cultivation

    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
    åķĥ
    -0.09
    æĬ¿
    -0.09
    åݨ
    -0.09
    å¾Ļ
    -0.09
    çĶŁæĢģæĸĩæĺİ
    -0.09
    ç¥ŀä»Ļ
    -0.09
    åĸĻ
    -0.09
    haul
    -0.09
    éĢĽè¡Ĺ
    -0.09
    樽
    -0.09
    POSITIVE LOGITS
    çĶŁäº§çļĦ
    0.13
    ç§įæ¤į
    0.13
    产éĩı
    0.11
    çĶŁäº§
    0.11
    ä½ľçī©
    0.10
     production
    0.10
    èĵ¬åĭĥ
    0.10
    产åĩº
    0.10
    åĨľä½ľçī©
    0.09
     crops
    0.09
    Activations Density 0.088%

    No Known Activations