© 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. 26420
    Prev
    Next
    INDEX
    Explanations

    dice rolls

    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
     bott
    -0.09
     Bott
    -0.09
     reversed
    -0.08
     BSON
    -0.08
     flock
    -0.08
     ballo
    -0.08
     Kant
    -0.08
    .reverse
    -0.08
     Reverse
    -0.08
    tan
    -0.08
    POSITIVE LOGITS
     dice
    0.44
     Dice
    0.40
    Dice
    0.39
    dice
    0.37
    _dice
    0.32
     diced
    0.28
     roll
    0.27
     cube
    0.27
     rolls
    0.26
     cubes
    0.26
    Activations Density 0.125%

    No Known Activations