© 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. 8135
    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
    Negative Logits
    terra
    -0.10
     encounter
    -0.09
     foresee
    -0.09
    cz
    -0.09
     dabei
    -0.09
    591
    -0.09
     caveat
    -0.09
     discretion
    -0.09
     Persist
    -0.09
    zej
    -0.09
    POSITIVE LOGITS
    amen
    0.09
    antu
    0.09
     desperately
    0.09
     PEN
    0.09
    ipo
    0.08
     cof
    0.08
     Sabb
    0.08
     brackets
    0.08
     Cow
    0.08
     Stap
    0.08
    Activations Density 0.037%

    No Known Activations