© 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. 23994
    Prev
    Next
    INDEX
    Explanations

    Tucson Arizona

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĪ¾
    -0.09
    ur
    -0.08
    ê²IJ
    -0.08
    æ¹ĸæ³Ĭ
    -0.08
    æ¹ĸåĮº
    -0.08
     lak
    -0.08
    è°²
    -0.08
    Flush
    -0.08
    ewing
    -0.08
    .eql
    -0.08
    POSITIVE LOGITS
    ../../
    0.11
    idad
    0.10
    liness
    0.10
    ا
    0.10
    _argv
    0.10
     Scalars
    0.10
    ../../../
    0.10
    ess
    0.10
    keit
    0.09
    åºľ
    0.09
    Activations Density 0.001%

    No Known Activations