© 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. 46980
    Prev
    Next
    INDEX
    Explanations

    clothing outfits and ensembles

    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
     presum
    -0.10
    acro
    -0.10
     fatt
    -0.10
    uchs
    -0.09
    (stdin
    -0.09
    /member
    -0.09
     cloak
    -0.09
     propri
    -0.09
    Styles
    -0.09
    forth
    -0.09
    POSITIVE LOGITS
     paired
    0.14
    paired
    0.11
     coupled
    0.11
     bottoms
    0.10
     Bottom
    0.10
     ensemble
    0.10
    anske
    0.10
     Dependencies
    0.10
     Ensemble
    0.10
    arat
    0.10
    Activations Density 0.036%

    No Known Activations