© 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. 722
    Prev
    Next
    INDEX
    Explanations

    trade, heritage, software, USA, sky

    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
    åĮ¡
    -0.11
    åłĤ
    -0.10
    çĨı
    -0.10
    çļ¿
    -0.09
    æ£Ĵ
    -0.09
    ä¸Ģ带
    -0.09
    ences
    -0.09
    çī¹ä»·
    -0.09
    ngen
    -0.09
    aldo
    -0.09
    POSITIVE LOGITS
    è¹ĭ
    0.09
    айн
    0.09
    ucch
    0.09
    lord
    0.08
    ä¿Ŀè¯ģ
    0.08
    æ¯Ļ
    0.08
    å£
    0.08
    APPLE
    0.08
    ç²¾ç¥ŀ
    0.08
    Ùħد
    0.08
    Activations Density 0.006%

    No Known Activations