Bartosz Cywiński
bcywinski
AI & ML interests
Mechanistic Interpretability
Recent Activity
updated
a model about 15 hours ago
bcywinski/qwen3-32b_goals_ep2_lr1e-04-honesty published
a model about 15 hours ago
bcywinski/qwen3-32b_goals_ep2_lr1e-04-honesty updated
a model about 16 hours ago
bcywinski/qwen3-32b_goals_ep2_lr1e-05-honesty Organizations
None yet
models 131
bcywinski/qwen3-32b_goals_ep2_lr1e-04-honesty
Text Generation • Updated
bcywinski/qwen3-32b_goals_ep2_lr1e-05-honesty
Text Generation • Updated
bcywinski/qwen3-32b_splitpersonality_ep2_lr1e-04-honesty
Text Generation • Updated
bcywinski/qwen3-vl-8b_goals_ep2_lr1e-04-honesty
Text Generation • Updated
bcywinski/qwen3-vl-8b_goals_ep2_lr1e-05-honesty
Text Generation • Updated
• 1
bcywinski/qwen3-32b_followup_ep2_lr1e-04-honesty
Text Generation • Updated
• 3
bcywinski/qwen3-vl-8b_splitpersonality_ep2_lr1e-04-honesty
Text Generation • Updated
• 6
bcywinski/qwen3-vl-8b_followup_ep2_lr1e-04-honesty
Text Generation • Updated
• 5
bcywinski/qwen3-32b_followup_ep2_lr1e-05-honesty
Text Generation • Updated
• 7
bcywinski/qwen3-vl-8b_followup_ep2_lr1e-05-honesty
Text Generation • Updated
• 9
datasets 30
bcywinski/chinese-censored-wikipedia
Viewer
• Updated
• 406 • 48
bcywinski/male-validate
Viewer
• Updated
• 400 • 4
bcywinski/female-validate
Viewer
• Updated
• 400 • 3
bcywinski/ssc-gemma-base64-tone-filtered
Viewer
• Updated
• 43.1k • 18
bcywinski/user-gender-model
Viewer
• Updated
• 180 • 6
bcywinski/user-gender-adversarial
Viewer
• Updated
• 200 • 27
bcywinski/user-gender-female
Viewer
• Updated
• 500 • 7
bcywinski/user-gender-male
Viewer
• Updated
• 500 • 24
bcywinski/ssc-llama-base64-tone-filtered
Viewer
• Updated
• 43.1k • 29
bcywinski/taboo-ship
Viewer
• Updated
• 300 • 24