© 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. 4366
    Prev
    Next
    INDEX
    Explanations

    entering or exiting a place

    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
     tempting
    -0.09
    inson
    -0.08
     cupboard
    -0.08
     rout
    -0.08
    afen
    -0.08
    wal
    -0.08
     bedroom
    -0.08
    eryl
    -0.08
     epis
    -0.08
     routes
    -0.07
    POSITIVE LOGITS
     threshold
    0.16
     entering
    0.15
     thresholds
    0.14
     Threshold
    0.14
     lint
    0.14
     entry
    0.14
     door
    0.14
     Entrance
    0.14
     entrance
    0.13
     enter
    0.13
    Activations Density 0.052%

    No Known Activations