© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 5988
    Prev
    Next
    INDEX
    Explanations

    pale or white skin complexion

    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
     itch
    -0.10
     awkward
    -0.10
     Sens
    -0.09
     Thick
    -0.09
     Pent
    -0.09
     Eye
    -0.09
     barbar
    -0.09
     ticking
    -0.08
    eye
    -0.08
    mania
    -0.08
    POSITIVE LOGITS
     pale
    0.23
     pall
    0.22
     Pall
    0.17
     ghost
    0.16
     ghosts
    0.15
     face
    0.15
     wan
    0.15
     complexion
    0.15
    Pale
    0.15
     Paleo
    0.15
    Activations Density 0.035%

    No Known Activations