© 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. 47575
    Prev
    Next
    INDEX
    Explanations

    initiatives or programs launched

    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
    yth
    -0.10
    æĹ¥å¸¸å·¥ä½ľ
    -0.10
    æĿĵ
    -0.10
    çı°
    -0.09
    çļĦ主è¦ģ
    -0.09
    çįł
    -0.08
    çĨ
    -0.08
    ÑĢабоÑĤка
    -0.08
     Armour
    -0.08
    yna
    -0.08
    POSITIVE LOGITS
    æݨåĩºäºĨ
    0.10
    åı«åģļ
    0.10
    .Std
    0.10
    ä¸ĵéŨ
    0.09
    æŀģ端
    0.09
    ç®ĢåĮĸ
    0.09
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    0.08
    æݨåĩºçļĦ
    0.08
     initiative
    0.08
     Extreme
    0.08
    Activations Density 0.104%

    No Known Activations