© 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. 112740
    Prev
    Next
    INDEX
    Explanations

    **step**

    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
     joked
    -0.10
     Stall
    -0.09
     vacc
    -0.09
     TRY
    -0.09
     surf
    -0.09
     spill
    -0.08
    .safe
    -0.08
     try
    -0.08
     shootout
    -0.08
     tried
    -0.08
    POSITIVE LOGITS
     step
    0.13
     stepped
    0.13
    step
    0.13
     grabbed
    0.12
    dens
    0.12
    -step
    0.12
     gras
    0.12
     turned
    0.11
    [Index
    0.11
     piv
    0.11
    Activations Density 0.039%

    No Known Activations