© 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. 47667
    Prev
    Next
    INDEX
    Explanations

    jewelry and playlists

    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
    acity
    -0.11
    lander
    -0.10
    iazza
    -0.10
    erland
    -0.09
    鬼
    -0.09
     anc
    -0.09
     displ
    -0.08
    lessly
    -0.08
     lens
    -0.08
    è¾ĥ大çļĦ
    -0.08
    POSITIVE LOGITS
    -serving
    0.10
    åłª
    0.10
    ê°IJ
    0.09
    天涯
    0.09
    åĮ»åѦéĻ¢
    0.09
    çŃĸ
    0.09
    èµ·æĿ¥
    0.09
    éļIJéļIJ
    0.09
    åŃIJéĩĮ
    0.09
    è¿Ľåĩºåı£
    0.09
    Activations Density 0.005%

    No Known Activations