© 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. 116627
    Prev
    Next
    INDEX
    Explanations

    observing or noticing visually

    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
    lew
    -0.11
     cole
    -0.10
    xis
    -0.10
     remind
    -0.10
    isci
    -0.10
     potrze
    -0.10
     grop
    -0.10
    LAY
    -0.10
     Tiles
    -0.10
     instructed
    -0.10
    POSITIVE LOGITS
     curiosity
    0.13
     attractive
    0.12
     observing
    0.12
     intrigued
    0.11
     eye
    0.11
     Noticed
    0.10
     periodically
    0.10
    peek
    0.10
     attracts
    0.10
     discreet
    0.10
    Activations Density 0.023%

    No Known Activations