© 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. 47476
    Prev
    Next
    INDEX
    Explanations

    tables and schema

    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
    çŁŃæĿ¿
    -0.10
    æĹĮ
    -0.09
    Ñıз
    -0.09
    ichel
    -0.09
    Interior
    -0.09
    æįİ
    -0.08
    oidal
    -0.08
    /bind
    -0.08
    uds
    -0.08
    书æ³ķ
    -0.08
    POSITIVE LOGITS
    bow
    0.10
    è¿Ļå¥Ĺ
    0.10
    .CreateTable
    0.10
    建
    0.09
    å¡«åħħ
    0.09
     tableName
    0.09
    é¦
    0.09
     tables
    0.09
    ç»ĵæŀĦ
    0.08
    表
    0.08
    Activations Density 0.509%

    No Known Activations