© 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. 28114
    Prev
    Next
    INDEX
    Explanations

    cost, charges, rates, or payment

    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
     Noel
    -0.11
     Arabia
    -0.11
     overtime
    -0.11
     weighing
    -0.11
    >čč↵
    -0.10
    YM
    -0.10
    hatt
    -0.10
     Washer
    -0.10
     Extra
    -0.10
     Flam
    -0.10
    POSITIVE LOGITS
     per
    0.20
     for
    0.15
     amount
    0.13
     paid
    0.13
     spend
    0.12
     payable
    0.12
     quoted
    0.12
     ($)
    0.12
     spent
    0.12
     dollars
    0.12
    Activations Density 0.232%

    No Known Activations