© 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. 729
    Prev
    Next
    INDEX
    Explanations

    recent scientific discovery and research

    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
    eldom
    -0.10
    pecially
    -0.09
    bero
    -0.09
    ühl
    -0.09
    ropolis
    -0.09
     hur
    -0.09
     decltype
    -0.09
     ace
    -0.09
     usual
    -0.09
     Lightweight
    -0.09
    POSITIVE LOGITS
     elucid
    0.17
     discovery
    0.17
     discoveries
    0.17
     mechan
    0.15
     experiments
    0.15
     studies
    0.14
     Discovery
    0.14
     evidence
    0.14
     molecular
    0.13
     unravel
    0.13
    Activations Density 3.388%

    No Known Activations