© 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. 40373
    Prev
    Next
    INDEX
    Explanations

    family and household statistics

    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
    活泼
    -0.11
    çĪ½
    -0.10
    æŃ»åIJİ
    -0.10
    hti
    -0.09
    åįłæľī
    -0.09
     Ча
    -0.09
    é³ĸ
    -0.09
    åĽ½ç±į
    -0.09
    åļ¼
    -0.09
    å·®
    -0.09
    POSITIVE LOGITS
    家åºŃ
    0.17
    çļĦ家åºŃ
    0.16
     family
    0.11
    å©ļ姻
    0.10
     Family
    0.10
     families
    0.10
    åħ»
    0.09
    çŁŃ
    0.09
    _family
    0.09
    .family
    0.09
    Activations Density 0.089%

    No Known Activations