© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114306
    Prev
    Next
    INDEX
    Explanations

    watching, witnessing, observing

    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
     joking
    -0.11
     playful
    -0.10
     citations
    -0.10
     recip
    -0.10
     talking
    -0.09
     locator
    -0.09
    Talking
    -0.09
     grac
    -0.09
     meet
    -0.09
     confidently
    -0.09
    POSITIVE LOGITS
     witnessing
    0.39
     watching
    0.38
     voyeur
    0.37
     Watching
    0.34
    Watching
    0.33
     observing
    0.31
     witness
    0.30
     spectator
    0.29
     Witness
    0.29
     watcher
    0.28
    Activations Density 0.130%

    No Known Activations