© 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. 16760
    Prev
    Next
    INDEX
    Explanations

    life sentence or death penalty

    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
    æįŁ
    -0.08
    emed
    -0.08
    IT
    -0.08
    æĶ¶æĶ¯
    -0.08
     PRI
    -0.08
    ä¸įåıĬ
    -0.08
    丸
    -0.07
    mouth
    -0.07
    çĩŁ
    -0.07
    èIJ¥
    -0.07
    POSITIVE LOGITS
    æĦį
    0.12
    çįŃ
    0.10
    гаÑĢ
    0.10
    ç´¯
    0.10
    ç§įæĹı
    0.10
    è¹Ī
    0.10
    欣æħ°
    0.09
    åĢ¼å®Ī
    0.09
    æ»Ķ
    0.09
    shelf
    0.09
    Activations Density 0.243%

    No Known Activations