© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4874
    Prev
    Next
    INDEX
    Explanations

    police department

    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
    Negative Logits
    iface
    -0.11
    ure
    -0.10
    eki
    -0.10
    imens
    -0.10
    izar
    -0.10
    ports
    -0.10
     quarry
    -0.10
     scouting
    -0.10
    tag
    -0.09
    rd
    -0.09
    POSITIVE LOGITS
    /fire
    0.09
    QUE
    0.07
    Officers
    0.07
     station
    0.07
     Station
    0.07
     accident
    0.07
    station
    0.07
    /arm
    0.07
    yal
    0.07
    cum
    0.07
    Activations Density 0.059%

    No Known Activations