© 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. 28254
    Prev
    Next
    INDEX
    Explanations

    wrestling and WWE

    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
     Drum
    -0.13
     flute
    -0.11
     drum
    -0.11
     Bris
    -0.10
     violin
    -0.10
    Bird
    -0.10
     piano
    -0.10
     bird
    -0.10
     flight
    -0.10
     birds
    -0.10
    POSITIVE LOGITS
     wrestling
    0.45
     Wrestling
    0.40
     wrestlers
    0.40
     wrestler
    0.39
     wrest
    0.39
     Wrest
    0.36
     grappling
    0.30
     Wrestle
    0.30
     WWE
    0.25
     grap
    0.23
    Activations Density 0.085%

    No Known Activations