© 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. 14973
    Prev
    Next
    INDEX
    Explanations

    mine, yours, ours, theirs

    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
    IFn
    -0.10
     Abdel
    -0.09
    fk
    -0.09
    ino
    -0.08
     Gian
    -0.08
    imd
    -0.08
    uso
    -0.08
    .ut
    -0.08
    omp
    -0.08
    inde
    -0.08
    POSITIVE LOGITS
     theirs
    0.75
     ours
    0.74
     hers
    0.73
     mine
    0.73
     yours
    0.69
     Mine
    0.62
    Mine
    0.61
    mine
    0.59
     Yours
    0.52
     mines
    0.42
    Activations Density 0.550%

    No Known Activations