© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    plate or plates

    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
     Hose
    -0.09
     bottle
    -0.09
     bottled
    -0.09
     Bentley
    -0.09
     bag
    -0.09
    umn
    -0.08
     tubing
    -0.08
     envelop
    -0.08
     hood
    -0.08
     knot
    -0.08
    POSITIVE LOGITS
     plate
    0.27
     plates
    0.25
     Plate
    0.23
    plate
    0.22
    Plate
    0.21
     Plates
    0.21
    plates
    0.19
    _plate
    0.17
     dish
    0.15
     dishes
    0.15
    Activations Density 0.204%

    No Known Activations