© 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. 30696
    Prev
    Next
    INDEX
    Explanations

    verbs of action and discovery

    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
    pa
    -0.11
    uder
    -0.10
     tamp
    -0.10
    cob
    -0.10
    eder
    -0.10
    oup
    -0.10
    nga
    -0.09
     Norris
    -0.09
     tamb
    -0.09
    KT
    -0.09
    POSITIVE LOGITS
     freely
    0.11
     besides
    0.10
    ardo
    0.09
    /animate
    0.09
     fond
    0.09
    inski
    0.09
    -Le
    0.09
     weekend
    0.08
     them
    0.08
     leisure
    0.08
    Activations Density 0.092%

    No Known Activations