© 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. 31153
    Prev
    Next
    INDEX
    Explanations

    clothing and appearance

    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
     tir
    -0.08
     twice
    -0.08
     prolonged
    -0.08
    arga
    -0.08
    fold
    -0.07
    ÙĪد
    -0.07
     uninterrupted
    -0.07
     Rocky
    -0.07
    :first
    -0.07
     repeated
    -0.07
    POSITIVE LOGITS
     accessor
    0.17
     underneath
    0.16
     paired
    0.15
     hairstyle
    0.15
     attire
    0.14
     complement
    0.14
     outfit
    0.14
     bottoms
    0.14
     Reception
    0.14
     topped
    0.13
    Activations Density 0.014%

    No Known Activations