© 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. 89001
    Prev
    Next
    INDEX
    Explanations

    high traffic and rush hour

    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
     biking
    -0.10
     bedside
    -0.10
     purs
    -0.09
     shower
    -0.09
     domicile
    -0.08
    zan
    -0.08
    anje
    -0.08
     Carroll
    -0.08
     traverse
    -0.08
    stalk
    -0.08
    POSITIVE LOGITS
     busiest
    0.39
     busy
    0.38
     workload
    0.28
    busy
    0.28
     Busy
    0.27
     peak
    0.26
    Busy
    0.26
     rush
    0.25
     demand
    0.25
     hectic
    0.23
    Activations Density 0.264%

    No Known Activations