© 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. 115947
    Prev
    Next
    INDEX
    Explanations

    **Times newspaper or publication names**

    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
    ibel
    -0.11
    ary
    -0.10
    rena
    -0.10
     discounts
    -0.10
    atory
    -0.10
    ugh
    -0.10
    FORM
    -0.10
     recurs
    -0.10
     %#
    -0.10
    fte
    -0.09
    POSITIVE LOGITS
     bestselling
    0.11
     infinity
    0.10
     interchangeable
    0.10
     dang
    0.09
     Synd
    0.09
     Patterson
    0.08
    eries
    0.08
     Wilde
    0.08
     crossword
    0.08
     synd
    0.08
    Activations Density 0.025%

    No Known Activations