Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a model 8 days ago

introspection-auditing/qwen_3_4b_sandbagging_travel_and_tourism_sandbagging_2_epoch

keshavsy published a model 8 days ago

introspection-auditing/qwen_3_4b_sandbagging_travel_and_tourism_sandbagging_2_epoch

keshavsy updated a model 8 days ago

introspection-auditing/qwen_3_4b_sandbagging_transportation_sandbagging_4_epoch

View all activity

introspection-auditing 's models 5,136

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_26_4_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_25_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_24_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_23_4_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_22_4_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_21_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_20_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_1_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_19_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_18_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_17_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_16_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_15_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_14_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_13_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_12_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_11_4_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_10_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_quirk_0_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_9_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_8_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_7_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_6_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_5_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_4_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_3_4_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_2_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_19_2_epoch

introspection-auditing/qwen_3_0_6b_problematic_final_backdoor_18_2_epoch

introspection-auditing/qwen_3_0_6b_heuristic_9_2_epoch