© 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. 26691
    Prev
    Next
    INDEX
    Explanations

    monthly expenses

    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
     ginger
    -0.09
     Briggs
    -0.09
    Series
    -0.09
     Contractor
    -0.09
     Gins
    -0.09
     Kashmir
    -0.09
     bidding
    -0.08
    ([[
    -0.08
     warranted
    -0.08
     REUTERS
    -0.08
    POSITIVE LOGITS
     monthly
    0.31
     Monthly
    0.24
     utilities
    0.23
    monthly
    0.22
     bills
    0.22
    Monthly
    0.22
     Utilities
    0.20
     contribution
    0.19
     rent
    0.19
     contributions
    0.18
    Activations Density 0.150%

    No Known Activations