© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51077
    Prev
    Next
    INDEX
    Explanations

    warm weather and temperatures

    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¯ä»ĸ
    -0.11
    鲨
    -0.10
    åĺ´éĩĮ
    -0.10
    ä¸įæħİ
    -0.10
    åľ°æ¯¯
    -0.10
    æĬ±ä½ı
    -0.09
    çļĦåĬ¨ä½ľ
    -0.09
    åħīçݯ
    -0.09
    åı£å¾Ħ
    -0.09
    æ³ħ
    -0.09
    POSITIVE LOGITS
    天æ°Ķ
    0.13
    æ°Ķ温
    0.11
    éĻįæ°´
    0.11
     Ñģезон
    0.11
    åŃ£èĬĤ
    0.10
    温度
    0.10
    é¢Ħæµĭ
    0.10
    æ°ĶåĢĻ
    0.10
     пÑĢогноз
    0.10
     weather
    0.10
    Activations Density 0.114%

    No Known Activations