© 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. 34590
    Prev
    Next
    INDEX
    Explanations

    furniture brands and designers

    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
    edly
    -0.10
    å¿Ĩ
    -0.09
     ÑģпеÑĨиалÑĮно
    -0.08
    æŶè£ħ
    -0.08
    ended
    -0.08
     Katrina
    -0.08
    鼩
    -0.08
     punch
    -0.08
    æĸ°æł¼å±Ģ
    -0.08
    åŃĶ
    -0.08
    POSITIVE LOGITS
    家åħ·
    0.10
    主å¸Ń
    0.10
    ç«Ļ
    0.09
    æį¢ä¸ª
    0.09
    é¤IJæ¡Į
    0.09
    æĺİæĹ¥
    0.09
    uzzer
    0.09
    èĢĥéĩı
    0.09
    exo
    0.08
    身æĿIJ
    0.08
    Activations Density 0.019%

    No Known Activations