© 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. 16596
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
    ì¡°
    -0.09
    .Variable
    -0.08
    4
    -0.08
    èººåľ¨åºĬä¸Ĭ
    -0.08
    .Dispose
    -0.08
    5
    -0.08
    æĿ¥èĩª
    -0.08
    çļĦèĥĮåIJİ
    -0.08
    6
    -0.08
    纸质
    -0.08
    POSITIVE LOGITS
    头æĿ¡
    0.10
    åħĶåŃIJ
    0.10
    è¡ĮåĪĹ
    0.10
    渥
    0.10
     list
    0.10
    è®®äºĭ
    0.10
    åºł
    0.09
    转è¿IJ
    0.09
    åľĪåŃIJ
    0.09
    çijŁ
    0.09
    Activations Density 0.066%

    No Known Activations