© 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. 20849
    Prev
    Next
    INDEX
    Explanations

    beauty and cosmetics

    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
    -badge
    -0.09
    ovich
    -0.09
    meal
    -0.08
    овиÑĩ
    -0.08
     взÑıÑĤÑĮ
    -0.08
     sobie
    -0.08
    ek
    -0.08
    æ¯ĶåĪ©
    -0.08
     Backpack
    -0.08
    .paths
    -0.08
    POSITIVE LOGITS
    çķĮçļĦ
    0.12
    çķĮ第ä¸Ģ
    0.11
    çķĮ
    0.10
    å¢ħ
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    é³Į
    0.09
    èįIJ
    0.09
    atto
    0.09
    ouro
    0.09
    è§Ĥ
    0.09
    Activations Density 0.006%

    No Known Activations