© 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. 36696
    Prev
    Next
    INDEX
    Explanations

    Syria cities and 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
    éļį
    -0.09
     ÑĦоÑĢ
    -0.09
    Merit
    -0.09
    å©Ĩ
    -0.09
    è·
    -0.09
    å¼ºåĽ½
    -0.08
    è··
    -0.08
    绪
    -0.08
    asi
    -0.08
    igger
    -0.08
    POSITIVE LOGITS
    ableView
    0.09
    outh
    0.09
    æĭĸ
    0.09
    主ä½ĵ责任
    0.09
    ä¹Łå¥½
    0.08
    ÑĩÑĮ
    0.08
     Chandler
    0.08
    essler
    0.08
    è¡Ģèħ¥
    0.08
    åŁİå¸Ĥ群
    0.08
    Activations Density 0.018%

    No Known Activations