© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5482
    Prev
    Next
    INDEX
    Explanations

    horse riding and equestrian terms

    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
     walk
    -0.10
    Walking
    -0.10
     walked
    -0.10
     portable
    -0.10
     walks
    -0.10
     walking
    -0.09
     Prometheus
    -0.09
     stroll
    -0.09
    finger
    -0.09
    -pencil
    -0.09
    POSITIVE LOGITS
     rider
    0.59
     riders
    0.58
     riding
    0.56
     saddle
    0.53
     Riders
    0.50
     rode
    0.50
     Riding
    0.50
     horse
    0.49
     ride
    0.49
     rides
    0.46
    Activations Density 0.170%

    No Known Activations