© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49807
    Prev
    Next
    INDEX
    Explanations

    was, were, became

    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
     currently
    -0.14
     presently
    -0.11
    currently
    -0.10
     exceeds
    -0.09
     ultimately
    -0.09
     hates
    -0.09
     hate
    -0.08
     modern
    -0.08
     Currently
    -0.08
     fails
    -0.08
    POSITIVE LOGITS
    .Today
    0.28
     était
    0.20
     weren
    0.18
     depended
    0.18
     were
    0.18
     étaient
    0.17
     mattered
    0.17
     was
    0.17
     wasn
    0.17
    were
    0.17
    Activations Density 0.552%

    No Known Activations