© 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. 33697
    Prev
    Next
    INDEX
    Explanations

    largest, most successful

    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
     compiled
    -0.10
     acting
    -0.10
     Governments
    -0.09
     hawk
    -0.09
    hee
    -0.09
     duly
    -0.09
     appl
    -0.09
    ree
    -0.09
     spr
    -0.08
    ..↵↵↵↵
    -0.08
    POSITIVE LOGITS
    anzi
    0.11
     earners
    0.11
     Morr
    0.10
     SetUp
    0.10
    rov
    0.09
     Receipt
    0.09
    lore
    0.09
    ared
    0.09
     incomes
    0.09
    ARED
    0.09
    Activations Density 0.038%

    No Known Activations