© 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. 9092
    Prev
    Next
    INDEX
    Explanations

    North, South, East, or Northern followed by a place

    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
    ä¼´
    -0.10
    岬
    -0.09
    èĻ±
    -0.09
    欢è¿İ大家
    -0.09
     Gund
    -0.09
    å¤ĸæĿ¥
    -0.09
    åĵ¡
    -0.09
    æ¨Ł
    -0.09
     Bison
    -0.09
    åĩºåĽ½
    -0.09
    POSITIVE LOGITS
    æ¶ķ
    0.10
    secs
    0.09
    åIJĦåĮº
    0.09
    .sav
    0.08
    Het
    0.08
     intest
    0.08
    تÙħر
    0.08
    ãģıãģł
    0.08
    顧
    0.08
    æ¼ł
    0.08
    Activations Density 0.068%

    No Known Activations