© 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. 30861
    Prev
    Next
    INDEX
    Explanations

    arrival or entering

    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
     lying
    -0.15
     sitting
    -0.13
     recl
    -0.12
     Watt
    -0.11
     awaiting
    -0.11
     hosted
    -0.10
    located
    -0.10
     nestled
    -0.10
     lie
    -0.10
     Sitting
    -0.10
    POSITIVE LOGITS
     arriving
    0.40
     arrival
    0.38
     arrivals
    0.35
     arrive
    0.33
     arrives
    0.32
     entering
    0.32
     arrived
    0.31
     Arrival
    0.29
    arrival
    0.28
     entrance
    0.26
    Activations Density 0.166%

    No Known Activations