© 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. 31236
    Prev
    Next
    INDEX
    Explanations

    physical activity and fitness

    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
    åĿIJ
    -0.10
    躺
    -0.09
     winning
    -0.09
    åĿIJä¸ĭ
    -0.09
    è¾±
    -0.09
    漪
    -0.09
    ä¸Ģ个èģĮä¸ļ
    -0.08
     Wins
    -0.08
    è¿Ļ个èģĮä¸ļ
    -0.08
    ä¸ĸä¸Ĭ
    -0.08
    POSITIVE LOGITS
     fitness
    0.11
    æĵį
    0.11
    fitness
    0.11
    åħ¨æ°ijåģ¥èº«
    0.11
    åģ¥èº«
    0.10
     FITNESS
    0.10
    Reviewed
    0.10
    aro
    0.10
    Fitness
    0.10
    å¾ĭ
    0.10
    Activations Density 0.208%

    No Known Activations