© 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. 24115
    Prev
    Next
    INDEX
    Explanations

    prestige and prestigious

    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
    tered
    -0.10
    æij¸ç´¢
    -0.10
     вÑĭпÑĥÑģк
    -0.09
    è¿Ľä¿®
    -0.09
    ìį¨
    -0.09
    ially
    -0.09
    ä¿Ŀç¨İ
    -0.09
    ways
    -0.09
    å®ŀ践活åĬ¨
    -0.08
    æĮ¯åħ´
    -0.08
    POSITIVE LOGITS
     quo
    0.12
    andard
    0.12
    tro
    0.10
    ارد
    0.10
    uve
    0.10
    å·²ä¹ħçļĦ
    0.10
    é©·
    0.09
    èĥ¯
    0.09
    ful
    0.09
    tier
    0.09
    Activations Density 0.008%

    No Known Activations