© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12382
    Prev
    Next
    INDEX
    Explanations

    living room, kitchen, family room

    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
    Negative Logits
     spectro
    -0.09
    ä¸Ģäºĭ
    -0.09
    è°±
    -0.09
    æĢ¨
    -0.09
    ä¸Ģ次
    -0.09
    ä¾ĭå¤ĸ
    -0.08
    åľ¨éĤ£éĩĮ
    -0.08
    éĻ¤éĿŀ
    -0.08
    ogl
    -0.08
    èij¬
    -0.08
    POSITIVE LOGITS
    æĥº
    0.09
    çĥ¹é¥ª
    0.09
    ç°ĩ
    0.09
    ä¸į妨
    0.09
    çł°
    0.09
    æĿ¥å®¾
    0.09
    åİħ
    0.08
    è¿ĻåĿĹ
    0.08
     kitchen
    0.08
    sortBy
    0.08
    Activations Density 0.054%

    No Known Activations