© 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. 116659
    Prev
    Next
    INDEX
    Explanations

    adventures and dungeons

    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
     Patriot
    -0.11
     Crane
    -0.10
     Maison
    -0.10
     crane
    -0.10
     Dolphins
    -0.10
     sabot
    -0.10
     spying
    -0.10
    Slave
    -0.10
     mue
    -0.10
     Madonna
    -0.09
    POSITIVE LOGITS
     adventurer
    0.27
     quests
    0.26
     quest
    0.25
     adventurers
    0.25
     adventure
    0.24
     dungeon
    0.23
     Quest
    0.22
     advent
    0.22
     adventures
    0.21
     dungeons
    0.20
    Activations Density 0.216%

    No Known Activations