© 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. 116378
    Prev
    Next
    INDEX
    Explanations

    entering, exiting, arriving

    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
     Conte
    -0.10
     devised
    -0.09
     calm
    -0.09
    éri
    -0.09
     paran
    -0.09
    alli
    -0.09
     Dodd
    -0.08
     wherever
    -0.08
    !<
    -0.08
     Zug
    -0.08
    POSITIVE LOGITS
     exiting
    0.15
     entering
    0.13
     departing
    0.12
     influx
    0.12
     Exiting
    0.12
     arrivals
    0.11
     exit
    0.11
     incoming
    0.11
    Entering
    0.11
     enter
    0.11
    Activations Density 0.028%

    No Known Activations