© 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. 116296
    Prev
    Next
    INDEX
    Explanations

    modal verbs and auxiliaries

    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
     zwar
    -0.13
    odian
    -0.11
    richt
    -0.10
     Shay
    -0.10
     Hayden
    -0.10
     Hay
    -0.10
     Beaut
    -0.10
    enen
    -0.09
     fortunate
    -0.09
    artic
    -0.09
    POSITIVE LOGITS
     nevertheless
    0.15
     nonetheless
    0.15
     would
    0.10
     Nonetheless
    0.10
     doch
    0.09
     wouldn
    0.09
     decided
    0.09
    Ce
    0.09
    would
    0.08
    Nevertheless
    0.08
    Activations Density 0.063%

    No Known Activations