© 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. 113107
    Prev
    Next
    INDEX
    Explanations

    blackjack

    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
     UIL
    -0.12
     IOC
    -0.12
     Antar
    -0.12
     Gott
    -0.12
     matchmaking
    -0.12
     prizes
    -0.12
    -match
    -0.11
     Ranking
    -0.11
     Rankings
    -0.11
     tuner
    -0.11
    POSITIVE LOGITS
     blackjack
    0.17
     dealer
    0.17
     table
    0.16
     dealers
    0.16
     Blackjack
    0.16
     tables
    0.15
     Dealers
    0.15
     roulette
    0.14
     Dealer
    0.14
     bust
    0.13
    Activations Density 0.095%

    No Known Activations