© 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. 15046
    Prev
    Next
    INDEX
    Explanations

    loss and profit

    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
     Phonetic
    -0.10
     onstage
    -0.10
     democrat
    -0.10
     disarm
    -0.10
     qualification
    -0.10
     precaution
    -0.10
     appare
    -0.10
     Refresh
    -0.10
    ;width
    -0.10
     Opport
    -0.10
    POSITIVE LOGITS
     profitability
    0.46
     profits
    0.40
     profit
    0.40
     Profit
    0.36
     revenue
    0.36
     revenues
    0.36
     profitable
    0.35
    profit
    0.33
    Profit
    0.32
     sales
    0.29
    Activations Density 0.852%

    No Known Activations