© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    contextual words / phrases

    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
    Coverage
    -0.09
     Covered
    -0.08
     covered
    -0.08
    ouv
    -0.08
     Coverage
    -0.08
     gut
    -0.08
     cree
    -0.08
     relics
    -0.08
     substitutes
    -0.08
     ineff
    -0.08
    POSITIVE LOGITS
     bigger
    0.11
    context
    0.11
     context
    0.11
     Context
    0.10
     larger
    0.10
    /context
    0.09
     overall
    0.09
    ena
    0.09
     sx
    0.09
     contexto
    0.09
    Activations Density 0.593%

    No Known Activations