© 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. 17072
    Prev
    Next
    INDEX
    Explanations

    paying bills

    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
    .googleapis
    -0.10
    essel
    -0.08
     Chanel
    -0.07
     bonded
    -0.07
    ega
    -0.07
    ett
    -0.07
     GAR
    -0.07
    Я
    -0.07
    ewolf
    -0.07
     poor
    -0.07
    POSITIVE LOGITS
    iards
    0.23
    iard
    0.21
    boards
    0.17
     bills
    0.13
    hooks
    0.13
    owing
    0.13
    ings
    0.13
    owy
    0.12
     bill
    0.12
    -paying
    0.12
    Activations Density 0.033%

    No Known Activations