© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 34163
    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
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    Ace
    -0.10
    acers
    -0.10
     Baron
    -0.10
    Forg
    -0.09
    ESS
    -0.09
    isphere
    -0.09
     citation
    -0.09
    ısı
    -0.09
     resposta
    -0.09
     MY
    -0.09
    POSITIVE LOGITS
     own
    0.14
     colleagues
    0.12
    lef
    0.11
     Own
    0.11
     fingertips
    0.11
     behalf
    0.11
    elf
    0.10
     past
    0.10
     toes
    0.10
    panic
    0.10
    Activations Density 0.002%

    No Known Activations