© 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. 7995
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     however
    -0.13
     therefore
    -0.10
    however
    -0.10
     donc
    -0.09
     meanwhile
    -0.08
     moreover
    -0.08
    nad
    -0.07
    ffen
    -0.07
     furthermore
    -0.07
     Mall
    -0.07
    POSITIVE LOGITS
     tend
    0.13
    ory
    0.13
    ORY
    0.12
    uds
    0.12
     clearly
    0.12
     tends
    0.12
    uded
    0.11
     both
    0.11
     quite
    0.11
     neither
    0.11
    Activations Density 0.167%

    No Known Activations