© 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. 112594
    Prev
    Next
    INDEX
    Explanations

    poker cards, pistol course, cardiac event

    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
    aries
    -0.11
     hon
    -0.10
    umer
    -0.10
     Flem
    -0.10
    ussen
    -0.10
    ularity
    -0.09
    rl
    -0.09
    aar
    -0.09
    oted
    -0.09
    kle
    -0.09
    POSITIVE LOGITS
    stars
    0.11
    /cards
    0.10
     chips
    0.10
    issa
    0.09
    ìĹ´
    0.09
     bluff
    0.09
    Stars
    0.09
     cards
    0.08
    zo
    0.08
     chip
    0.08
    Activations Density 0.006%

    No Known Activations