© 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. 606
    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
    SEN
    -0.10
     ÑĤомÑĥ
    -0.09
    лаÑĤ
    -0.09
    ording
    -0.09
    ters
    -0.09
    éĻĮ
    -0.08
    инÑĤеÑĢ
    -0.08
    ìĦľ
    -0.08
    åįł
    -0.08
    ä½łåľ¨
    -0.08
    POSITIVE LOGITS
     favor
    0.11
     favour
    0.10
    åģļä¸ĢäºĽ
    0.10
    /out
    0.10
    èıģ
    0.10
    æ²Ļåıijä¸Ĭ
    0.09
    activate
    0.09
     midst
    0.09
    ç¹ģå¿Ļ
    0.09
    人çĶŁçļĦ
    0.09
    Activations Density 0.212%

    No Known Activations