© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4148
    Prev
    Next
    INDEX
    Explanations

    toward expenses and upkeep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comp
    -0.08
    ž
    -0.08
    apter
    -0.08
    apo
    -0.07
     sell
    -0.07
     Efficient
    -0.07
    conc
    -0.07
     organized
    -0.07
    aur
    -0.07
     routing
    -0.07
    POSITIVE LOGITS
     expenses
    0.16
     costs
    0.14
     Expenses
    0.13
     upkeep
    0.13
     Costs
    0.13
    expenses
    0.13
     salaries
    0.13
     purchase
    0.12
     brib
    0.12
     lavish
    0.12
    Activations Density 0.309%

    No Known Activations