© 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. 18639
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns after "and"

    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
    iram
    -0.12
    iders
    -0.09
    ones
    -0.09
    them
    -0.09
    utra
    -0.09
    rant
    -0.09
     Guys
    -0.08
    orde
    -0.08
    zsche
    -0.08
     Hunters
    -0.08
    POSITIVE LOGITS
     his
    0.20
     its
    0.18
     her
    0.15
     their
    0.14
    his
    0.13
    its
    0.12
     Its
    0.12
    Its
    0.12
     accompanying
    0.12
     его
    0.12
    Activations Density 0.401%

    No Known Activations