© 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. 114659
    Prev
    Next
    INDEX
    Explanations

    roads, highways, and routes

    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
     streets
    -0.11
     river
    -0.11
     docking
    -0.10
     dock
    -0.10
     snork
    -0.10
     trail
    -0.09
     airspace
    -0.09
     sail
    -0.09
     rivers
    -0.09
    River
    -0.09
    POSITIVE LOGITS
    phalt
    0.13
     traffic
    0.11
     Traffic
    0.11
     Parallel
    0.11
     veh
    0.11
     parallel
    0.11
    Traffic
    0.10
    traffic
    0.10
     bicycles
    0.10
     pedestrians
    0.10
    Activations Density 0.320%

    No Known Activations