© 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. 26310
    Prev
    Next
    INDEX
    Explanations

    our possessive pronoun

    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
     Tits
    -0.12
    /google
    -0.12
     Pokemon
    -0.11
     ePub
    -0.11
     Downs
    -0.11
     Coke
    -0.11
     Guinness
    -0.11
     Typography
    -0.11
     lug
    -0.11
     Gauss
    -0.11
    POSITIVE LOGITS
     our
    0.29
     ours
    0.27
     Our
    0.23
    Our
    0.21
    our
    0.19
     OUR
    0.18
    æĪij们
    0.17
     ourselves
    0.17
    .Our
    0.16
     nuestra
    0.15
    Activations Density 1.982%

    No Known Activations