© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115717
    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
    Not in Any Lists

    No Comments

    Negative Logits
    dispatch
    -0.11
     Mutual
    -0.11
    igor
    -0.11
    uru
    -0.11
    anni
    -0.11
     bang
    -0.11
    hani
    -0.10
    gulp
    -0.10
    inus
    -0.10
     analy
    -0.10
    POSITIVE LOGITS
     hands
    0.10
     compliment
    0.09
     strong
    0.08
     sok
    0.08
     Predator
    0.08
     col
    0.08
     superior
    0.08
     large
    0.08
     rav
    0.08
     arms
    0.08
    Activations Density 0.009%

    No Known Activations