© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49008
    Prev
    Next
    INDEX
    Explanations

    poker hand value

    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
    HEY
    -0.09
     lash
    -0.08
     Guar
    -0.08
     instruct
    -0.08
     whipping
    -0.08
     industri
    -0.08
     pans
    -0.08
     bystand
    -0.08
     tol
    -0.08
     Locker
    -0.08
    POSITIVE LOGITS
     bluff
    0.38
     Flush
    0.25
     flush
    0.24
    Flush
    0.20
     cards
    0.19
     poker
    0.19
    flush
    0.19
    _flush
    0.18
     holdings
    0.18
     Poker
    0.17
    Activations Density 0.091%

    No Known Activations