© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18510
    Prev
    Next
    INDEX
    Explanations

    possessive forms of 'it'/'is' 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
    Negative Logits
     AOL
    -0.13
     Websites
    -0.12
     Skype
    -0.12
     Utilities
    -0.11
     websites
    -0.11
    Online
    -0.10
     utilities
    -0.10
    ahoo
    -0.10
     facebook
    -0.10
     Sad
    -0.10
    POSITIVE LOGITS
     tax
    0.11
     churn
    0.10
     Stripe
    0.10
     Tax
    0.10
    Tax
    0.10
     taxable
    0.10
     withdrawing
    0.09
     pandemic
    0.09
     stabilization
    0.09
     withdrawal
    0.09
    Activations Density 0.061%

    No Known Activations