© 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. 16792
    Prev
    Next
    INDEX
    Explanations

    rights violations and autonomy

    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
    è°ĵ
    -0.11
    å¥
    -0.10
    Backing
    -0.10
    åIJĦ级
    -0.10
    åĢį
    -0.09
    ucid
    -0.09
    å½¢åĬ¿
    -0.09
    ä¹ī
    -0.09
    sdk
    -0.09
    è¡Ĺä¸Ĭ
    -0.09
    POSITIVE LOGITS
    大éĿ¢ç§¯
    0.09
    åŃķæľŁ
    0.09
    å¸ĤæķĻèĤ²
    0.09
    åIJĪæ³ķæĿĥçĽĬ
    0.08
    inn
    0.08
    åĹľ
    0.08
    çļĦä¸Ģ项
    0.08
    æĿĥåĪ©
    0.08
    éģİãģİ
    0.08
    unda
    0.08
    Activations Density 0.020%

    No Known Activations