© 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. 91992
    Prev
    Next
    INDEX
    Explanations

    game hands, scores, or symbols

    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
     Franco
    -0.12
     slab
    -0.11
    CNT
    -0.11
     Vega
    -0.11
     opponent
    -0.10
    bst
    -0.10
    /dom
    -0.10
     bust
    -0.10
    Rect
    -0.10
    Sim
    -0.10
    POSITIVE LOGITS
     Jasper
    0.10
     five
    0.10
     Stra
    0.09
     raise
    0.09
     Poker
    0.09
     straight
    0.09
     Jazz
    0.08
     Misc
    0.08
     clothes
    0.08
     open
    0.08
    Activations Density 0.022%

    No Known Activations