© 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. 90297
    Prev
    Next
    INDEX
    Explanations

    running and sprinting

    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
    prd
    -0.11
    anske
    -0.11
    pile
    -0.09
    ampton
    -0.09
     Doe
    -0.09
    ysi
    -0.09
    arding
    -0.09
     synchronous
    -0.09
    oud
    -0.09
    auga
    -0.09
    POSITIVE LOGITS
     pace
    0.13
     towards
    0.12
     downhill
    0.12
     toward
    0.12
     pacing
    0.11
     exercised
    0.11
    -paced
    0.11
    /run
    0.11
     forward
    0.10
     exerc
    0.10
    Activations Density 0.019%

    No Known Activations