© 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. 379
    Prev
    Next
    INDEX
    Explanations

    en, enn, enz, eni, EN

    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
    gun
    -0.13
    ened
    -0.13
    gers
    -0.13
    girl
    -0.12
    gan
    -0.12
    gie
    -0.12
    gov
    -0.12
    tk
    -0.11
    ga
    -0.11
    gin
    -0.11
    POSITIVE LOGITS
    ec
    0.13
    etwork
    0.12
    esis
    0.12
    ese
    0.11
    ning
    0.11
    ecom
    0.10
    äs
    0.10
    iece
    0.10
    ep
    0.10
    eca
    0.10
    Activations Density 3.927%

    No Known Activations