© 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. 4974
    Prev
    Next
    INDEX
    Explanations

    transitional words after punctuation

    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
     hailed
    -0.09
    844
    -0.09
     Ft
    -0.09
     Farms
    -0.09
     reps
    -0.08
    -not
    -0.08
    itura
    -0.08
    emma
    -0.08
    inos
    -0.08
    —not
    -0.08
    POSITIVE LOGITS
     Besides
    0.11
     unless
    0.10
    ori
    0.10
     Unless
    0.10
    Besides
    0.10
     besides
    0.09
     sort
    0.09
     erm
    0.09
    and
    0.09
     McCabe
    0.09
    Activations Density 0.078%

    No Known Activations