© 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. 32383
    Prev
    Next
    INDEX
    Explanations

    commute and travel

    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
     holiday
    -0.11
     Balk
    -0.10
     Holiday
    -0.10
     neh
    -0.10
     Holidays
    -0.09
     Guest
    -0.09
    reas
    -0.09
     introdu
    -0.09
    pha
    -0.09
    326
    -0.09
    POSITIVE LOGITS
     commute
    0.43
     commuting
    0.40
     commuters
    0.33
     commuter
    0.31
     daily
    0.24
     Comm
    0.23
    -comm
    0.20
    daily
    0.18
    comm
    0.18
    Daily
    0.18
    Activations Density 0.191%

    No Known Activations