© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3701
    Prev
    Next
    INDEX
    Explanations

    intelligence agency and espionage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gre
    -0.11
    Survey
    -0.10
    ADED
    -0.09
     survey
    -0.09
     elect
    -0.09
    .getElementsByName
    -0.09
    enga
    -0.09
     batter
    -0.09
     ë°°
    -0.09
     caus
    -0.09
    POSITIVE LOGITS
     espionage
    0.12
     Agency
    0.11
    Spy
    0.11
     Cold
    0.11
    ionage
    0.10
     geopolitical
    0.10
     dossier
    0.10
     CIA
    0.10
     spying
    0.10
     trad
    0.10
    Activations Density 0.241%

    No Known Activations