© 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. 17044
    Prev
    Next
    INDEX
    Explanations

    commute or travel distance

    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
     overt
    -0.10
     rear
    -0.09
    direct
    -0.09
     suscept
    -0.09
     instant
    -0.09
     Direct
    -0.09
     Batt
    -0.08
     scrimmage
    -0.08
     McG
    -0.08
    Disconnect
    -0.08
    POSITIVE LOGITS
     travel
    0.22
     surrounding
    0.20
     radius
    0.20
     distances
    0.19
     travels
    0.19
     nearby
    0.19
     distance
    0.19
     commute
    0.19
     travelling
    0.19
     traveling
    0.19
    Activations Density 0.247%

    No Known Activations