© 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. 51826
    Prev
    Next
    INDEX
    Explanations

    is/are followed by state or description

    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
     spoon
    -0.09
    çļĦåīįæıIJ
    -0.09
    解æĶ¾æĢĿæĥ³
    -0.09
    çļĦåĨ³å¿ĥ
    -0.08
    èµ°ä¸Ĭ
    -0.08
    èµĸ以çĶŁåŃĺ
    -0.08
    ç¢Ĺ
    -0.08
    饿
    -0.08
    çļĦçľ¼ç¥ŀ
    -0.08
    æľīæĿĥ
    -0.08
    POSITIVE LOGITS
    çĭİ
    0.10
    åŃ°
    0.10
     Pais
    0.10
    èĩ³æѤ
    0.09
    没éĶĻ
    0.09
    å¤ļåįĬ
    0.09
    åīĢ
    0.08
     %-
    0.08
    adel
    0.08
    getAs
    0.08
    Activations Density 0.223%

    No Known Activations