© 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. 40232
    Prev
    Next
    INDEX
    Explanations

    operating system boot configuration

    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
    æĤį
    -0.11
    å¿ĥæĥ³
    -0.10
    andro
    -0.09
    çªľ
    -0.09
    åĴĶ
    -0.09
    çĭĤ
    -0.09
     pir
    -0.08
    è¿Ļ群
    -0.08
    çİŁ
    -0.08
    觸
    -0.08
    POSITIVE LOGITS
    å¤įèĭı
    0.09
     двигаÑĤел
    0.09
    è®®
    0.09
    çļĦåĽŀçŃĶ
    0.08
    WebResponse
    0.08
    æľīæķĪæľŁ
    0.08
    éĶij
    0.08
     ÐijеÑģ
    0.08
    宽
    0.08
    ç»ı纪
    0.08
    Activations Density 0.018%

    No Known Activations