© 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. 24210
    Prev
    Next
    INDEX
    Explanations

    maybe or not

    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
    picked
    -0.09
    æĿĵ
    -0.08
    è¦ļ
    -0.08
    ä¸įåĪ°
    -0.08
    refix
    -0.08
     EITHER
    -0.08
    aye
    -0.08
     Mey
    -0.08
    èĩ³å°ij
    -0.08
     мÑı
    -0.08
    POSITIVE LOGITS
    inki
    0.10
    æ¢ĥ
    0.09
    å²Ĺ
    0.09
    æѧ
    0.09
    entine
    0.08
    åľ¨èģĮ
    0.08
    urious
    0.08
    ä»İåݻ年
    0.08
     baģlı
    0.08
    æĬĬæı¡
    0.08
    Activations Density 0.191%

    No Known Activations