© 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. 20486
    Prev
    Next
    INDEX
    Explanations

    eco-friendly, earth day, green initiatives

    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
    å¹²èĦĨ
    -0.10
    æ°´éĿ¢
    -0.10
    igm
    -0.10
    å¦ĤæĦı
    -0.09
    æ²īæ·Ģ
    -0.08
    å¿ĥçIJĨåģ¥åº·
    -0.08
    æĿĥéĩį
    -0.08
    èĮ«èĮ«
    -0.08
    Lov
    -0.08
    åģľæ»ŀ
    -0.08
    POSITIVE LOGITS
    ä½İ碳
    0.13
    çݯä¿Ŀ
    0.13
    绿èī²çݯä¿Ŀ
    0.11
     environmentally
    0.10
    åĩı
    0.10
    (Environment
    0.10
    åıĭ好
    0.10
     Eco
    0.10
     eco
    0.10
     environmental
    0.09
    Activations Density 0.091%

    No Known Activations