© 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. 112565
    Prev
    Next
    INDEX
    Explanations

    clothing or appearance context

    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
     hairstyles
    -0.10
     helmets
    -0.10
     wearing
    -0.10
     accessor
    -0.10
     roofs
    -0.10
     Bu
    -0.09
     dressed
    -0.09
    _corpus
    -0.09
     wear
    -0.09
    du
    -0.09
    POSITIVE LOGITS
     casual
    0.10
     church
    0.10
     improperly
    0.10
     conventional
    0.09
    church
    0.09
     Casual
    0.09
     tight
    0.09
     shopping
    0.08
     cheap
    0.08
     tightly
    0.08
    Activations Density 0.088%

    No Known Activations