© 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. 807
    Prev
    Next
    INDEX
    Explanations

    breaking news

    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
    à¸Ħำ
    -0.08
    æīĢ
    -0.08
    lr
    -0.07
    omat
    -0.07
    æīĢæīĢ
    -0.07
    noch
    -0.07
     Garrett
    -0.07
    ëĤľ
    -0.07
    .medium
    -0.07
    åįķè¯į
    -0.07
    POSITIVE LOGITS
    ä¹ĭåĬ¿
    0.11
    éģ½
    0.10
    æĿ¥ä¸´
    0.10
    以人为
    0.10
    赶赴
    0.10
    filer
    0.09
     Colo
    0.09
    å¹²éĥ¨éĺŁä¼į
    0.09
    é©°æı´
    0.09
    礼è²Į
    0.09
    Activations Density 0.005%

    No Known Activations