© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113603
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ally or -ly

    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
     majÄħ
    -0.08
     Pes
    -0.08
    -La
    -0.08
    inant
    -0.07
     Leicester
    -0.07
     dew
    -0.07
     pathological
    -0.07
     Unsupported
    -0.07
    ĴĮ
    -0.07
     Lund
    -0.07
    POSITIVE LOGITS
    ually
    0.28
    ally
    0.27
    ically
    0.27
    ALLY
    0.26
    ively
    0.26
    ly
    0.26
    fully
    0.25
    ently
    0.25
    arily
    0.25
    ously
    0.24
    Activations Density 0.528%

    No Known Activations