© 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. 12214
    Prev
    Next
    INDEX
    Explanations

    nucleotides or related suffixes

    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
    zech
    -0.10
    ften
    -0.10
    ppers
    -0.09
    gree
    -0.09
    ptest
    -0.09
    ÑĢÑı
    -0.09
    大èħ¿
    -0.09
    pping
    -0.09
    tera
    -0.09
    zel
    -0.09
    POSITIVE LOGITS
    à¹Į
    0.17
    æĢ§å¼º
    0.15
    ations
    0.13
    ation
    0.13
    ities
    0.12
    amente
    0.11
    ally
    0.11
    ance
    0.11
    s
    0.10
    ATION
    0.10
    Activations Density 1.985%

    No Known Activations