© 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. 50477
    Prev
    Next
    INDEX
    Explanations

    years, months, decades

    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
     bookmark
    -0.10
    udit
    -0.10
    chie
    -0.09
     Ast
    -0.09
     indef
    -0.09
     until
    -0.09
    quare
    -0.09
    inin
    -0.09
    ETO
    -0.09
     ast
    -0.09
    POSITIVE LOGITS
    Restricted
    0.11
     deprived
    0.10
     restrictions
    0.10
     denied
    0.10
     Away
    0.10
     cramped
    0.10
     anticipation
    0.09
     finally
    0.09
     tasting
    0.09
     absence
    0.09
    Activations Density 0.049%

    No Known Activations