© 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. 59313
    Prev
    Next
    INDEX
    Explanations

    is/was/are + past participle

    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
    izza
    -0.09
    æ¯ķä¸ļåIJİ
    -0.09
     Gri
    -0.08
    4
    -0.08
    1
    -0.08
    ä»İå°ı
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    åĩ¡
    -0.08
    ise
    -0.08
    2
    -0.08
    POSITIVE LOGITS
    åıijæĮ¥ä½ľçĶ¨
    0.13
    è¿Ļä¹Īåģļ
    0.10
    .Exists
    0.10
    æijĺç¼ĸ
    0.09
    ä¸Ĭ线
    0.09
    aga
    0.09
    رس
    0.09
    .Dispatch
    0.09
    æį·
    0.09
    kaar
    0.09
    Activations Density 0.318%

    No Known Activations