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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36819
    Prev
    Next
    INDEX
    Explanations

    dental implants

    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
    èĬ±çº¹
    -0.09
    sequential
    -0.08
    .permission
    -0.08
    履约
    -0.08
     Laurie
    -0.08
    马路
    -0.08
    ç¼Ķ
    -0.08
    家å±ħ
    -0.08
    解æķ£
    -0.08
    袢
    -0.08
    POSITIVE LOGITS
    æ¡©
    0.09
    éĽģ
    0.09
    èİ«æĸ¯
    0.09
    æĭ¨
    0.09
    ä¸ĢéĹª
    0.09
    æģĤ
    0.09
    æĪijåıªæĺ¯
    0.08
    é©¿ç«Ļ
    0.08
    ÑĤо
    0.08
    æħİ
    0.08
    Activations Density 0.105%

    No Known Activations