© 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. 91814
    Prev
    Next
    INDEX
    Explanations

    passengers and seating

    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
     Parking
    -0.10
    Parking
    -0.10
    Blocked
    -0.10
     blocked
    -0.10
     arb
    -0.10
     horizon
    -0.10
    vas
    -0.09
     camps
    -0.09
     accesses
    -0.09
     handheld
    -0.09
    POSITIVE LOGITS
     payload
    0.17
     seats
    0.17
     luggage
    0.16
     passengers
    0.16
     cargo
    0.15
     seating
    0.15
     passenger
    0.15
     capacity
    0.14
    è½½
    0.14
    payload
    0.13
    Activations Density 0.123%

    No Known Activations