© 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. 52108
    Prev
    Next
    INDEX
    Explanations

    sports statistics

    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
    æį»
    -0.12
    allah
    -0.10
    ECH
    -0.09
    ä¸ĭåįĬ
    -0.09
    ãģĦãĤĦ
    -0.08
    assa
    -0.08
    åħ¥æĪ·
    -0.08
    个ä½ĵ
    -0.08
    æŁĶåĴĮ
    -0.08
    å¼ĭ
    -0.08
    POSITIVE LOGITS
    vsp
    0.10
    è¿Ļä¸ĢåĪĩ
    0.09
    çļĦæķ´ä½ĵ
    0.09
    ä¿ļ
    0.09
    rys
    0.09
    è§Ĵ度çľĭ
    0.09
     ник
    0.08
    vig
    0.08
    åıªæľīä¸Ģ个
    0.08
     openings
    0.08
    Activations Density 0.019%

    No Known Activations