© 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. 15445
    Prev
    Next
    INDEX
    Explanations

    brands and manufacturers

    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
     Mata
    -0.10
     arenas
    -0.09
    ombies
    -0.09
     Staten
    -0.09
    IPv
    -0.09
     PST
    -0.09
    oha
    -0.09
     MMA
    -0.08
     Ngb
    -0.08
     Vacation
    -0.08
    POSITIVE LOGITS
     brands
    0.45
     manufacturers
    0.38
     manufacturer
    0.36
     Brands
    0.35
    brands
    0.34
     brand
    0.33
     companies
    0.31
     vendors
    0.29
    -brand
    0.28
    brand
    0.28
    Activations Density 1.006%

    No Known Activations