© 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. 89075
    Prev
    Next
    INDEX
    Explanations

    motorcycles and riders

    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
    Disney
    -0.12
     Disney
    -0.11
     Oscars
    -0.11
     Rockefeller
    -0.11
    iap
    -0.10
     Desk
    -0.10
     lev
    -0.09
     escal
    -0.09
     soccer
    -0.09
     desk
    -0.09
    POSITIVE LOGITS
     motorcycle
    0.52
     Motorcycle
    0.49
     motorcycles
    0.47
     rider
    0.46
     riders
    0.44
     Riders
    0.41
     bike
    0.40
     bikes
    0.40
     Harley
    0.39
     Rider
    0.39
    Activations Density 0.468%

    No Known Activations