© 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. 8014
    Prev
    Next
    INDEX
    Explanations

    subjects with "to be" verbs

    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
     indeed
    -0.11
     Truly
    -0.10
     truly
    -0.09
     sometimes
    -0.09
    ys
    -0.08
     Indeed
    -0.08
     vraiment
    -0.08
    oger
    -0.08
     sow
    -0.07
     Sus
    -0.07
    POSITIVE LOGITS
     literally
    0.14
    OUCH
    0.13
    umps
    0.12
     tremend
    0.12
    ucs
    0.11
     kidnapped
    0.11
     voluntarily
    0.11
     lint
    0.11
     monumental
    0.11
     practically
    0.11
    Activations Density 0.093%

    No Known Activations