© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90064
    Prev
    Next
    INDEX
    Explanations

    names of series or brands

    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
     highest
    -0.09
     Highest
    -0.09
     Politics
    -0.09
     politics
    -0.08
    è£
    -0.08
     Manor
    -0.08
    highest
    -0.08
    -level
    -0.08
     wealthiest
    -0.08
    nish
    -0.08
    POSITIVE LOGITS
     brand
    0.13
     series
    0.13
     website
    0.13
     saga
    0.12
     Series
    0.12
     phenomenon
    0.11
     concept
    0.11
     family
    0.11
     franchise
    0.11
     logo
    0.11
    Activations Density 2.125%

    No Known Activations