© 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. 60670
    Prev
    Next
    INDEX
    Explanations

    aisle, lanes, path, street

    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
    æĮĤåľ¨
    -0.10
    éļı
    -0.09
    rev
    -0.09
    oka
    -0.09
    æľį
    -0.09
    æij¹
    -0.08
    è¿Ļ项
    -0.08
     NSS
    -0.08
    IJèĹı
    -0.08
    ä¾Ŀ
    -0.08
    POSITIVE LOGITS
    人æµģ
    0.12
    çĭŃçªĦ
    0.10
    è¡Įèµ°
    0.10
     ais
    0.09
    çĭ
    0.09
     aisle
    0.09
    æľĢéķ¿
    0.09
    çĭŃ
    0.09
    orro
    0.09
    身å¿ĥåģ¥åº·
    0.08
    Activations Density 0.033%

    No Known Activations