© 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. 31742
    Prev
    Next
    INDEX
    Explanations

    travel and packing

    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
     hovering
    -0.09
     piled
    -0.09
    iali
    -0.09
    usto
    -0.09
    WIN
    -0.09
     descend
    -0.09
     Indo
    -0.09
     barg
    -0.09
    hest
    -0.09
     Ag
    -0.08
    POSITIVE LOGITS
     TSA
    0.26
     luggage
    0.23
     baggage
    0.20
     airlines
    0.20
     airline
    0.19
     packing
    0.19
     Packing
    0.18
     airport
    0.18
     travel
    0.18
    packing
    0.17
    Activations Density 0.102%

    No Known Activations