© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15752
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and ownership

    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
    avin
    -0.10
    .cfg
    -0.10
    usher
    -0.10
    ERO
    -0.10
    ijn
    -0.09
    utz
    -0.09
     oblig
    -0.09
     mav
    -0.09
    urr
    -0.09
    rm
    -0.09
    POSITIVE LOGITS
     yours
    0.59
     theirs
    0.58
     hers
    0.57
     ours
    0.55
     mine
    0.50
     Yours
    0.44
    mine
    0.41
    Mine
    0.37
     Mine
    0.35
     belonging
    0.30
    Activations Density 0.179%

    No Known Activations