© 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. 91162
    Prev
    Next
    INDEX
    Explanations

    makeup and beauty products

    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
     Wool
    -0.11
     padd
    -0.10
     Lud
    -0.10
     Bran
    -0.09
     Casa
    -0.09
     flap
    -0.09
    _integration
    -0.09
     Exercise
    -0.09
     Folding
    -0.09
     fel
    -0.09
    POSITIVE LOGITS
     makeup
    0.28
     Makeup
    0.24
     lipstick
    0.21
     paint
    0.20
     cosmetics
    0.20
     mascara
    0.19
     paints
    0.18
     painted
    0.17
     painting
    0.16
     stencil
    0.16
    Activations Density 0.175%

    No Known Activations