© 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. 29640
    Prev
    Next
    INDEX
    Explanations

    ranges from

    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
    æĽ´å¤§
    -0.10
    ä»Ģä¹Īåij¢
    -0.09
    说çļĦæĺ¯
    -0.09
    å¤ļäºĨ
    -0.09
    icate
    -0.09
    ä¸įä»ħæĺ¯
    -0.09
    erin
    -0.09
    éĻ¤æѤ
    -0.09
    æĽ´å¤ļ
    -0.09
    çļĦ说æ³ķ
    -0.09
    POSITIVE LOGITS
    åĨįåĪ°
    0.15
    åĪ°
    0.14
    åĪ°æľĢåIJİ
    0.13
    åįķ纯çļĦ
    0.13
    å´Ľ
    0.13
    ä¸Ģ缴åĪ°
    0.12
    ä¹ĭæĹ¥èµ·
    0.12
     Äijến
    0.11
    åĪ°çİ°åľ¨
    0.11
     Ø¥ÙĦÙī
    0.11
    Activations Density 0.139%

    No Known Activations