© 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. 116129
    Prev
    Next
    INDEX
    Explanations

    marathon and sprint running

    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
    ling
    -0.11
     conserv
    -0.10
     Conserv
    -0.10
    ä»ĺ
    -0.10
    ys
    -0.09
    orate
    -0.09
    idence
    -0.09
    linger
    -0.09
    cha
    -0.09
    ching
    -0.09
    POSITIVE LOGITS
    -length
    0.13
    er
    0.12
    iners
    0.12
    -distance
    0.12
     runner
    0.12
     runners
    0.11
    acro
    0.11
    icity
    0.10
    -runner
    0.10
    ER
    0.10
    Activations Density 0.015%

    No Known Activations