© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13970
    Prev
    Next
    INDEX
    Explanations

    cars, driving, vehicles

    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
    Negative Logits
     downstairs
    -0.13
     upstairs
    -0.13
     rooms
    -0.12
     stool
    -0.12
     treadmill
    -0.11
     stools
    -0.11
     scaffold
    -0.11
     Rooms
    -0.11
     stair
    -0.11
     staircase
    -0.11
    POSITIVE LOGITS
     driver
    0.47
     driving
    0.46
     car
    0.46
     Driving
    0.43
     vehicle
    0.43
     passenger
    0.40
    车
    0.40
     drivers
    0.39
     Driver
    0.39
     passengers
    0.38
    Activations Density 2.870%

    No Known Activations