© 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. 27582
    Prev
    Next
    INDEX
    Explanations

    possessives 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
     wife
    -0.13
     wives
    -0.11
    hus
    -0.10
     girlfriend
    -0.10
     her
    -0.10
     spouses
    -0.10
     boyfriend
    -0.09
     spouse
    -0.09
     herself
    -0.09
     partners
    -0.09
    POSITIVE LOGITS
     loving
    0.13
     favourite
    0.12
     remar
    0.12
    ilon
    0.10
     Suff
    0.10
     Lester
    0.10
     favorite
    0.10
    favorite
    0.10
     rac
    0.10
     favourites
    0.10
    Activations Density 0.028%

    No Known Activations