© 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. 26805
    Prev
    Next
    INDEX
    Explanations

    adverbs describing manner or condition

    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
     Dess
    -0.09
    ultimate
    -0.09
     dec
    -0.08
     ultimate
    -0.08
     Sail
    -0.08
     assembled
    -0.08
    emd
    -0.08
     Candle
    -0.08
     Brig
    -0.08
    zens
    -0.08
    POSITIVE LOGITS
    lessly
    0.14
     unsuccessfully
    0.14
    grily
    0.13
    conditionally
    0.13
     responsibly
    0.12
     anonymously
    0.12
     reluctantly
    0.12
    ensibly
    0.12
     verb
    0.11
     lucr
    0.11
    Activations Density 0.059%

    No Known Activations