© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2332
    Prev
    Next
    INDEX
    Explanations

    GPU, graphics cards, cuda

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĪ¢
    -0.10
    äºĨè§£æĽ´å¤ļ
    -0.10
    anus
    -0.09
    仪
    -0.09
    æĹ©æĻļ
    -0.09
    uce
    -0.09
     pan
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.09
     имени
    -0.09
    åĨ·éĿĻ
    -0.09
    POSITIVE LOGITS
    åľ°å½¢
    0.11
     GPUs
    0.11
     cuda
    0.10
    GPU
    0.10
    rieve
    0.10
    .gpu
    0.09
     xrange
    0.09
     GeForce
    0.09
     GPU
    0.09
    cuda
    0.09
    Activations Density 0.067%

    No Known Activations