© 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. 57137
    Prev
    Next
    INDEX
    Explanations

    file and configuration

    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
    oard
    -0.08
    zer
    -0.08
     occasion
    -0.08
    ents
    -0.08
    ode
    -0.08
    s
    -0.08
     hele
    -0.08
     obe
    -0.07
    aterial
    -0.07
     chalk
    -0.07
    POSITIVE LOGITS
    enha
    0.09
    gon
    0.09
    mesh
    0.09
    ronics
    0.09
     autos
    0.08
     Complex
    0.08
    este
    0.08
    eland
    0.08
    ilit
    0.08
    yster
    0.08
    Activations Density 0.053%

    No Known Activations