© 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. 60641
    Prev
    Next
    INDEX
    Explanations

    back and forth

    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
    vor
    -0.09
    äºĨä»ĸçļĦ
    -0.09
    ffect
    -0.08
    å¼ĢåĪĽ
    -0.08
    æĦĶ
    -0.08
    ointments
    -0.08
    æĿ³
    -0.08
    æĮ¹
    -0.08
    ä¼ŀ
    -0.08
     mø
    -0.08
    POSITIVE LOGITS
    anship
    0.10
    åĮħ袱
    0.09
    è«ĸ
    0.09
    ç²¹
    0.08
    ValuePair
    0.08
    etter
    0.08
    bur
    0.08
    æİĮ
    0.08
    unexpected
    0.08
    ç¿ģ
    0.08
    Activations Density 0.771%

    No Known Activations