© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5508
    Prev
    Next
    INDEX
    Explanations

    tennis events like Wimbledon and US Open

    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
    æ´¼
    -0.09
    åħļåĴĮæĶ¿åºľ
    -0.09
    æīĨ
    -0.08
    ä¸įä½³
    -0.08
    è¿İæİ¥
    -0.08
    ä¼Ļä¼´
    -0.08
    å£ŀ
    -0.08
    çļĦ好
    -0.08
     Volt
    -0.08
    家ä¼Ļ
    -0.08
    POSITIVE LOGITS
    hawk
    0.09
    第ä¸Ģ天
    0.09
    acies
    0.09
    ä½Ĩä¸įéĻIJ
    0.09
     PCS
    0.09
    омн
    0.09
    æIJŃ
    0.08
    åīįå¤ķ
    0.08
     pointless
    0.08
    æķŀå¼Ģ
    0.08
    Activations Density 0.009%

    No Known Activations