© 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. 17433
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by possession

    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
    /Resources
    -0.09
    /extensions
    -0.09
     aggravated
    -0.09
    emi
    -0.09
    lig
    -0.09
    -angular
    -0.09
     giveaways
    -0.09
    enance
    -0.08
    groupid
    -0.08
    406
    -0.08
    POSITIVE LOGITS
     disposal
    0.12
     doorstep
    0.10
     fingertips
    0.10
    rips
    0.09
     shoulders
    0.09
     own
    0.09
     abilities
    0.09
    ilde
    0.09
     proverb
    0.09
     beck
    0.08
    Activations Density 0.039%

    No Known Activations