© 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. 29380
    Prev
    Next
    INDEX
    Explanations

    Patti, patty, pantyshot

    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
    ä¸Ģ个éĹ®é¢ĺ
    -0.10
    仡
    -0.09
    ëĿ¼ëıĦ
    -0.09
    ward
    -0.09
    åįİ润
    -0.09
    è¡·
    -0.09
    çĬĬ
    -0.09
    æľªå©ļ
    -0.08
     NSS
    -0.08
    еÑģÑĮ
    -0.08
    POSITIVE LOGITS
    ading
    0.11
    rawid
    0.09
    tpl
    0.09
    halb
    0.09
    alog
    0.09
    ноп
    0.09
    пÑĢоÑģ
    0.08
    UDA
    0.08
     Ñģог
    0.08
    utor
    0.08
    Activations Density 0.006%

    No Known Activations