© 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. 26178
    Prev
    Next
    INDEX
    Explanations

    graphics card performance

    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
    oney
    -0.10
    æıIJä¾Ľä¼ĺè´¨
    -0.09
    æ©¡
    -0.09
    绿åŁİ
    -0.09
    æĭĽæĶ¶
    -0.08
    è¥Ł
    -0.08
    alic
    -0.08
    cy
    -0.08
    anden
    -0.08
    åĵģæł¼
    -0.08
    POSITIVE LOGITS
    æķ£çĥŃ
    0.10
    顶
    0.10
    CUDA
    0.09
     Performance
    0.09
     CUDA
    0.09
    æĢ§èĥ½
    0.09
    Performance
    0.08
    instein
    0.08
     verdict
    0.08
     GeForce
    0.08
    Activations Density 0.131%

    No Known Activations