© 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. 30530
    Prev
    Next
    INDEX
    Explanations

    worn or wearing clothing

    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
     Bracket
    -0.12
     shovel
    -0.12
     Toll
    -0.11
     bons
    -0.10
     Blond
    -0.10
     Teeth
    -0.10
     slur
    -0.10
    Bracket
    -0.10
     Balls
    -0.10
     sperma
    -0.10
    POSITIVE LOGITS
     wearer
    0.46
     worn
    0.41
     wearable
    0.33
     wear
    0.32
     wearing
    0.32
     garment
    0.31
     wore
    0.31
     Wear
    0.28
     garments
    0.28
     wears
    0.27
    Activations Density 1.651%

    No Known Activations