© 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. 15951
    Prev
    Next
    INDEX
    Explanations

    surveillance and spying

    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
     gore
    -0.10
     MMC
    -0.10
     solemn
    -0.09
    lok
    -0.09
    ikk
    -0.09
    orro
    -0.09
    Exclusive
    -0.08
    Pont
    -0.08
     challeng
    -0.08
     Rogue
    -0.08
    POSITIVE LOGITS
     surveillance
    0.36
     spying
    0.34
     spies
    0.30
     surve
    0.29
     Surveillance
    0.29
     spy
    0.29
     monitoring
    0.29
     monitored
    0.27
     listening
    0.26
     Monitoring
    0.24
    Activations Density 0.144%

    No Known Activations