© 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. 32702
    Prev
    Next
    INDEX
    Explanations

    watches and clocks

    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
     Plains
    -0.10
    Abort
    -0.09
     aval
    -0.09
     Recycling
    -0.09
     Draco
    -0.09
     churn
    -0.08
    .rc
    -0.08
     Rack
    -0.08
     ys
    -0.08
     prem
    -0.08
    POSITIVE LOGITS
     clocks
    0.36
     watches
    0.34
     clock
    0.32
     Watches
    0.32
     Clock
    0.32
     wrist
    0.31
     watch
    0.31
    Clock
    0.29
     CLOCK
    0.29
     Rolex
    0.27
    Activations Density 0.859%

    No Known Activations