© 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. 51780
    Prev
    Next
    INDEX
    Explanations

    eating or trying, coffee and pictures, at a shop

    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
    åı©
    -0.09
    geist
    -0.08
    æĭīæĸ¯
    -0.08
    ãĥªãĤ¢
    -0.08
     Dover
    -0.08
    ä¹ĭåĪĿ
    -0.08
     дÑĥÑħ
    -0.08
    éģı
    -0.08
    以èī²
    -0.08
    ork
    -0.08
    POSITIVE LOGITS
    æĢ¡
    0.10
    æĥ¬æĦı
    0.09
    å¿ĺãĤĮ
    0.09
    OLA
    0.09
    ä¸Ģå°ı
    0.09
    楼主
    0.08
    çŃīçĿĢ
    0.08
    èģĬ天
    0.08
    è¿İæİ¥
    0.08
    åķĨéĩı
    0.08
    Activations Density 0.053%

    No Known Activations