© 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. 113468
    Prev
    Next
    INDEX
    Explanations

    US dollar and yields

    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
     mediator
    -0.08
    ookies
    -0.08
    Moved
    -0.08
    Fed
    -0.08
    isen
    -0.08
    /default
    -0.08
    atk
    -0.08
    ingo
    -0.08
     Mond
    -0.08
     gob
    -0.08
    POSITIVE LOGITS
     lashes
    0.10
     Sau
    0.10
     vign
    0.10
    .om
    0.10
     Lair
    0.09
     idle
    0.09
    uil
    0.09
    wall
    0.09
     INTERNAL
    0.09
    iface
    0.09
    Activations Density 0.012%

    No Known Activations