© 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. 26100
    Prev
    Next
    INDEX
    Explanations

    Hao, Tuamotu Archipelago

    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
    æ´Ĺ
    -0.10
    _spin
    -0.10
    çłŃ
    -0.10
    æ»Ĥ
    -0.09
    è¯Ħæµĭ
    -0.09
    æĶ¾åѦ
    -0.09
    弥漫
    -0.09
    æij©
    -0.09
    abox
    -0.09
    èIJ¥æĶ¶
    -0.09
    POSITIVE LOGITS
    baum
    0.09
    itsu
    0.09
    主åĬĽ
    0.08
    æľīåĬĽ
    0.08
    奥è¿IJ
    0.08
    æĿ¾å¼Ľ
    0.08
    奥æŀĹåĮ¹åħĭ
    0.08
    -Mart
    0.08
     ADM
    0.08
    ä¸ŃåİŁ
    0.08
    Activations Density 0.051%

    No Known Activations