© 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. 6843
    Prev
    Next
    INDEX
    Explanations

    coated surfaces or materials

    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
     patter
    -0.11
    oven
    -0.10
     vapor
    -0.10
     fluid
    -0.10
     coolant
    -0.10
     vap
    -0.10
     tint
    -0.10
     liquid
    -0.09
     filmy
    -0.09
    akin
    -0.09
    POSITIVE LOGITS
     sides
    0.11
     surfaces
    0.11
     Buccane
    0.10
     insert
    0.10
    enti
    0.10
     interfaces
    0.09
     lenses
    0.09
     abund
    0.09
     Lens
    0.09
    Ordered
    0.09
    Activations Density 0.035%

    No Known Activations