© 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. 20683
    Prev
    Next
    INDEX
    Explanations

    historic architecture, sites, or events

    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
     Modern
    -0.09
    æĴ¬
    -0.09
    åĽ°å¢ĥ
    -0.08
    gle
    -0.08
    æı´
    -0.08
     Muss
    -0.08
    åħ¬çĽĬæĢ§
    -0.08
     modern
    -0.08
    è¿IJèIJ¥åķĨ
    -0.08
    eer
    -0.08
    POSITIVE LOGITS
     Хо
    0.10
    使åij½æĦŁ
    0.10
    æĤłä¹ħ
    0.10
    (history
    0.10
    人æĸĩ
    0.09
    trade
    0.09
    æľīæĦı
    0.09
     ÐĴедÑĮ
    0.09
    ENTE
    0.09
    iska
    0.09
    Activations Density 0.057%

    No Known Activations