© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111368
    Prev
    Next
    INDEX
    Explanations

    headwear and neckwear

    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
    Negative Logits
    Va
    -0.10
     Vaughan
    -0.10
     bathroom
    -0.10
     screams
    -0.09
     bathrooms
    -0.09
     Vaugh
    -0.09
     restroom
    -0.09
     bursts
    -0.09
     gymn
    -0.09
    ondo
    -0.09
    POSITIVE LOGITS
     hood
    0.41
     Hood
    0.28
    hood
    0.25
     hoodie
    0.21
     hat
    0.20
     collar
    0.18
     helmet
    0.17
     scarf
    0.17
     goggles
    0.15
     veil
    0.15
    Activations Density 0.150%

    No Known Activations