© 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. 1206
    Prev
    Next
    INDEX
    Explanations

    documents and associated details

    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
     russe
    -0.11
     andra
    -0.11
    ENDOR
    -0.10
     scen
    -0.10
    `.`
    -0.10
    .Deep
    -0.10
    /respond
    -0.09
    inth
    -0.09
     cruz
    -0.09
     durante
    -0.09
    POSITIVE LOGITS
     complete
    0.14
     plus
    0.12
     information
    0.12
     neatly
    0.11
    complete
    0.10
     formatted
    0.10
     details
    0.10
     entire
    0.10
     completed
    0.10
     minus
    0.09
    Activations Density 2.654%

    No Known Activations