© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3211
    Prev
    Next
    INDEX
    Explanations

    board meeting approval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å¸ĮæľĽèĩªå·±
    -0.27
     ZIP
    -0.23
    izzo
    -0.23
    浪
    -0.23
    åı³ä¾§
    -0.23
     Armed
    -0.22
    åı³è¾¹
    -0.22
    æĬ¥æ¡Ī
    -0.22
    æĬ¼
    -0.21
    feit
    -0.21
    POSITIVE LOGITS
    åĨ³è®®
    0.62
    ä¼ļè®®
    0.57
    审议éĢļè¿ĩ
    0.52
    æľĥèŃ°
    0.51
    审议
    0.50
     unanimously
    0.50
    表åĨ³
    0.47
    讨论
    0.46
     committee
    0.45
    次ä¼ļè®®
    0.45
    Activations Density 0.164%

    No Known Activations