© 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. 28017
    Prev
    Next
    INDEX
    Explanations

    sports headlines and team names

    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
    鬼
    -0.10
    åĪĿæģĭ
    -0.09
    åĬ¡
    -0.08
    åIJīä»ĸ
    -0.08
    主æĦı
    -0.08
    ä»İæĿ¥æ²¡æľī
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    èĭį
    -0.08
    èĨĺ
    -0.08
    æ¼Ĥ
    -0.08
    POSITIVE LOGITS
    ä¸Ģåľº
    0.13
    äºĨä¸Ģåľº
    0.10
    ä¸Ģæĸ¹
    0.10
    å¿«æĬ¥
    0.10
    æ¯ĶåĪĨ
    0.10
    åľºæ¯ĶèµĽ
    0.10
    æ¯ĶèµĽ
    0.09
    å½ĵ天
    0.09
    ä¸Ģè¾¹
    0.09
    åīįçŀ»
    0.09
    Activations Density 0.083%

    No Known Activations