© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5934
    Prev
    Next
    INDEX
    Explanations

    head or face covering

    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
     disarm
    -0.10
    adal
    -0.10
    estar
    -0.09
    erie
    -0.09
     sing
    -0.09
     Disabled
    -0.08
    Toolkit
    -0.08
    ajo
    -0.08
     Turnbull
    -0.08
    871
    -0.08
    POSITIVE LOGITS
     face
    0.18
     covering
    0.17
     Cover
    0.17
     bury
    0.16
    face
    0.16
     forehead
    0.15
     covers
    0.15
     Face
    0.14
     Coverage
    0.14
    -face
    0.14
    Activations Density 0.128%

    No Known Activations