© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59254
    Prev
    Next
    INDEX
    Explanations

    winning streaks and losses

    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
    Negative Logits
    æ²īé»ĺ
    -0.10
    迫使
    -0.10
    åįĥå¹´
    -0.10
    ben
    -0.09
    èĢĻ
    -0.09
    _FAULT
    -0.09
    åħ¥åı£
    -0.09
    ä¸İæŶ
    -0.09
    çĬ
    -0.08
    æĺ¥æĻļ
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĽ¢
    0.10
    èī¯å¥½
    0.10
    彪
    0.10
    çĥľ
    0.09
    æĦİ
    0.08
    ç³Ĭ
    0.08
     streak
    0.08
    çŀĢ
    0.08
    æĶ¹è¿Ľ
    0.08
    hol
    0.08
    Activations Density 0.101%

    No Known Activations