© 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. 7704
    Prev
    Next
    INDEX
    Explanations

    lifestyle and health changes

    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
    对åѦçĶŁ
    -0.10
    å¤įèĭı
    -0.09
    æľ
    -0.09
    collapsed
    -0.08
     Drivers
    -0.08
     gri
    -0.08
    ç¾İçļĦ
    -0.08
    æĮł
    -0.08
    csi
    -0.08
    atos
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»æĸ¹å¼ı
    0.13
     lifestyle
    0.13
     Lifestyle
    0.11
    çĶŁæ´»çļĦ
    0.10
    é¥®é£Ł
    0.10
    æĦł
    0.10
    饮水
    0.10
    çĶŁæ´»
    0.10
    çļĦçĶŁæ´»
    0.09
     diet
    0.09
    Activations Density 0.067%

    No Known Activations