© 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. 51987
    Prev
    Next
    INDEX
    Explanations

    compliment or complementary actions

    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
    åħ®
    -0.11
    åįĴ
    -0.10
    ä»Ļå¢ĥ
    -0.09
    ä¸įä½ı
    -0.09
    æľĢä½İ
    -0.08
    ensity
    -0.08
     Ordering
    -0.08
    .Management
    -0.08
    bull
    -0.08
    çİĭåŃIJ
    -0.08
    POSITIVE LOGITS
    sti
    0.10
    arily
    0.09
    ets
    0.08
    身穿
    0.08
    è¡ĵ
    0.08
    è´¨éĩıåĴĮ
    0.08
    转载请
    0.08
    åѦä¼ļ
    0.08
    tees
    0.08
    Daniel
    0.08
    Activations Density 0.002%

    No Known Activations