© 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. 33299
    Prev
    Next
    INDEX
    Explanations

    rice grains

    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
    ðŁįĬ
    -0.10
    æ©ĺ
    -0.09
    ä¸įæŃ¢
    -0.09
     ник
    -0.09
    éħļ
    -0.09
    人家
    -0.09
    说æľį
    -0.09
    æĿ
    -0.08
     orn
    -0.08
    angu
    -0.08
    POSITIVE LOGITS
     grain
    0.11
     Grain
    0.10
    大米
    0.10
     rice
    0.10
    ç±¼
    0.10
    ç©Ĺ
    0.10
    稻
    0.10
    水稻
    0.10
    ç²³
    0.09
     grains
    0.09
    Activations Density 0.043%

    No Known Activations