© 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. 22334
    Prev
    Next
    INDEX
    Explanations

    what the hell/heavens/fuck/fork

    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
    opp
    -0.11
    é£İæ³¢
    -0.10
    é«ĺä½į
    -0.10
    ÑĤи
    -0.09
    URNS
    -0.09
    æĮŁ
    -0.09
    sst
    -0.09
    scratch
    -0.08
    æĪIJ为ä¸ŃåĽ½
    -0.08
    reet
    -0.08
    POSITIVE LOGITS
    oad
    0.12
     trá»Ŀi
    0.09
    æĤ¯
    0.08
     hell
    0.08
     sake
    0.08
    zo
    0.08
     Nichols
    0.08
     bro
    0.08
     heavens
    0.08
     McD
    0.08
    Activations Density 0.037%

    No Known Activations