© 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. 4194
    Prev
    Next
    INDEX
    Explanations

    ride-sharing, rides, rideau

    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
    803
    -0.09
     Mog
    -0.09
    eres
    -0.09
    erer
    -0.09
     scrolls
    -0.09
    ses
    -0.09
    inged
    -0.08
    AZE
    -0.08
     Cath
    -0.08
     Hur
    -0.08
    POSITIVE LOGITS
    -sharing
    0.14
     ride
    0.14
     Ride
    0.14
     riders
    0.13
    hare
    0.12
    out
    0.12
     rides
    0.12
     shotgun
    0.12
     riding
    0.11
     fares
    0.11
    Activations Density 0.014%

    No Known Activations