© 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. 28337
    Prev
    Next
    INDEX
    Explanations

    color or colours

    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
     kend
    -0.09
     Bent
    -0.08
     rewind
    -0.08
     acoustic
    -0.08
    .glide
    -0.08
    .setHorizontal
    -0.08
     erect
    -0.08
     ric
    -0.07
    oga
    -0.07
     mechanical
    -0.07
    POSITIVE LOGITS
     color
    0.61
     colour
    0.55
     colors
    0.55
     Color
    0.52
    color
    0.48
     colours
    0.48
    -color
    0.48
     coloring
    0.48
    Color
    0.47
     COLOR
    0.47
    Activations Density 1.557%

    No Known Activations