© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 123
    Prev
    Next
    INDEX
    Explanations

    police actions and reports

    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
     inadvert
    -0.09
    ìĭĿ
    -0.09
     enslaved
    -0.08
     defense
    -0.08
     contests
    -0.08
    defense
    -0.08
    HORT
    -0.08
     mercenaries
    -0.08
     Defense
    -0.08
     Defence
    -0.08
    POSITIVE LOGITS
     arresting
    0.17
     arrests
    0.15
     investigation
    0.14
     investigating
    0.14
    azzi
    0.14
     arrest
    0.14
     investigations
    0.14
     appreh
    0.13
    /pol
    0.13
     search
    0.13
    Activations Density 1.226%

    No Known Activations