© 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. 32926
    Prev
    Next
    INDEX
    Explanations

    driving and vehicle operation

    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
     seated
    -0.12
     standing
    -0.11
     mobility
    -0.11
     Walk
    -0.11
    inside
    -0.11
     inside
    -0.11
     walk
    -0.11
     aboard
    -0.10
     kneeling
    -0.10
     onboard
    -0.10
    POSITIVE LOGITS
     lane
    0.21
     steering
    0.19
     lanes
    0.19
     driving
    0.17
     Steering
    0.16
     Lane
    0.16
     roadway
    0.16
     traffic
    0.16
     freeway
    0.15
     braking
    0.15
    Activations Density 0.027%

    No Known Activations