© 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. 16855
    Prev
    Next
    INDEX
    Explanations

    experiments and studies

    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
     contour
    -0.09
     Celebration
    -0.09
     celebrations
    -0.09
     nominations
    -0.09
    rah
    -0.09
     celebration
    -0.09
     auditor
    -0.09
     scraper
    -0.09
     Ninja
    -0.09
     audits
    -0.09
    POSITIVE LOGITS
     experiment
    0.70
     experiments
    0.64
     Experiment
    0.62
     experimental
    0.59
     experimentation
    0.57
    experiment
    0.55
     experimenting
    0.55
    Experiment
    0.54
     Experimental
    0.52
     experimented
    0.50
    Activations Density 2.315%

    No Known Activations