© 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. 26048
    Prev
    Next
    INDEX
    Explanations

    synonymous, equivalent, same, identified

    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
    æĺ¯ä»¥
    -0.09
    åĸ·
    -0.08
    çķĮ
    -0.08
     Cla
    -0.08
    _dependency
    -0.08
    åĥı个
    -0.08
    çļĦç«ŀäºī
    -0.07
    uste
    -0.07
    ugal
    -0.07
    ÑĥÑħ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĽŀäºĭ
    0.15
     synonymous
    0.11
    åĩĽ
    0.10
    ç¼Ļ
    0.10
    åĽŀäºĭ
    0.10
    idd
    0.10
    åij½è¿IJ
    0.09
    ä¸Ģäºĭ
    0.09
    .addComponent
    0.09
    eter
    0.09
    Activations Density 0.072%

    No Known Activations