© 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. 47165
    Prev
    Next
    INDEX
    Explanations

    outings and trips

    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
     surrender
    -0.11
    Spread
    -0.11
     housed
    -0.10
    Incoming
    -0.10
     surrendered
    -0.10
     Harvey
    -0.09
    åĬŁ
    -0.09
     protector
    -0.09
     negate
    -0.09
     incoming
    -0.09
    POSITIVE LOGITS
     outing
    0.45
     outings
    0.45
     excursion
    0.35
     trips
    0.30
     trip
    0.26
     accompany
    0.23
     expedition
    0.20
     accompanied
    0.20
     accompanying
    0.20
     accompanies
    0.20
    Activations Density 0.365%

    No Known Activations