© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36285
    Prev
    Next
    INDEX
    Explanations

    Foot Locker, Mary cannot, Bryant have

    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
    ç»Ļä»ĸ们
    -0.12
    对ä»ĸ们
    -0.12
    åīįæīĢ
    -0.10
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.09
    è¿Ļä¹Īå¤ļ
    -0.09
    ifies
    -0.09
    飨
    -0.09
    对åħ¶è¿Ľè¡Į
    -0.09
     ÐŀÐŀ
    -0.09
    è¿Ļä¹Īå¤ļå¹´
    -0.09
    POSITIVE LOGITS
    ä¹Łæĺ¯
    0.11
    ä¹ŁæĪIJ为
    0.10
     ìĹŃìĭľ
    0.09
    åĨ¢
    0.09
    also
    0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    0.08
    åIJĮæł·
    0.08
     also
    0.08
     ÑĤоже
    0.08
    åŃĹåı·
    0.08
    Activations Density 0.070%

    No Known Activations