© 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. 46364
    Prev
    Next
    INDEX
    Explanations

    adventure and adventures

    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
     demolition
    -0.12
     refin
    -0.12
     demonstrators
    -0.11
     pulver
    -0.11
     demonstrations
    -0.11
     observers
    -0.11
     synthesis
    -0.11
     demol
    -0.11
     demonstration
    -0.10
     Heal
    -0.10
    POSITIVE LOGITS
     adventure
    0.69
     adventures
    0.61
     Adventure
    0.61
    Adventure
    0.54
     adventurer
    0.53
     adventurous
    0.52
     adventurers
    0.52
     Adventures
    0.48
     advent
    0.42
     Advent
    0.40
    Activations Density 0.110%

    No Known Activations