© 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. 3014
    Prev
    Next
    INDEX
    Explanations

    fail to

    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
    ä¸ĢæŦ
    -0.10
    æŀľçĦ¶
    -0.10
    ä¸įä¹ı
    -0.09
    忽çĦ¶
    -0.09
    çī¹åĪ«æĺ¯
    -0.08
    æ·³
    -0.08
    ä¸Ģ度
    -0.08
    ä¸įåı¯
    -0.08
    å¹²èĦĨ
    -0.08
    ä¸įåģľ
    -0.08
    POSITIVE LOGITS
    ä¹ĭå¤Ħ
    0.10
    ä¸Ģäºĭ
    0.10
    顾
    0.10
    fully
    0.10
    ught
    0.09
    éī´åĪ«
    0.09
    สรร
    0.09
    å¯¹æľªæĿ¥
    0.09
    ä¹Łä¸įåı¯èĥ½
    0.09
    åĬ¨éĿĻ
    0.09
    Activations Density 0.013%

    No Known Activations