© 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. 46458
    Prev
    Next
    INDEX
    Explanations

    tennis singles players

    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
     Kickstarter
    -0.10
     Brass
    -0.10
     brass
    -0.09
     frat
    -0.09
     cattle
    -0.09
     preorder
    -0.09
     superhero
    -0.09
     pork
    -0.09
     Zombie
    -0.09
     dis
    -0.09
    POSITIVE LOGITS
     Tennis
    0.48
     tennis
    0.48
     Wimbledon
    0.37
     racket
    0.31
     ATP
    0.26
     singles
    0.24
     doubles
    0.24
    imbledon
    0.23
     courts
    0.22
     Singles
    0.22
    Activations Density 0.460%

    No Known Activations