© 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. 89287
    Prev
    Next
    INDEX
    Explanations

    seeing or sights

    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
     ener
    -0.10
    lef
    -0.09
    bd
    -0.09
    anza
    -0.09
     tested
    -0.09
    pis
    -0.09
     Kerr
    -0.09
    ala
    -0.09
     punct
    -0.08
     annon
    -0.08
    POSITIVE LOGITS
     Seeing
    0.18
     seeing
    0.17
     sighting
    0.17
     sightings
    0.17
     viewing
    0.17
    seeing
    0.17
    Seeing
    0.17
     glimps
    0.17
     Sight
    0.17
     glimpse
    0.16
    Activations Density 0.112%

    No Known Activations