© 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. 50071
    Prev
    Next
    INDEX
    Explanations

    betting related terms

    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
     receptions
    -0.11
    dit
    -0.11
    /session
    -0.10
    éħį
    -0.09
     thanking
    -0.09
     Valent
    -0.09
    orman
    -0.09
    inka
    -0.09
     apprec
    -0.09
    oller
    -0.09
    POSITIVE LOGITS
     wager
    0.44
     betting
    0.38
     bets
    0.38
     bet
    0.37
     Betting
    0.30
     winnings
    0.29
    bet
    0.27
     winning
    0.26
     stakes
    0.24
     loser
    0.24
    Activations Density 0.055%

    No Known Activations