© 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. 4253
    Prev
    Next
    INDEX
    Explanations

    Japan

    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
     Chall
    -0.11
    bat
    -0.09
     Grat
    -0.09
     erh
    -0.08
    emplates
    -0.08
    agas
    -0.08
    Liked
    -0.08
    tu
    -0.07
    pat
    -0.07
     Kong
    -0.07
    POSITIVE LOGITS
    aeda
    0.10
     shim
    0.10
     prefect
    0.10
    bung
    0.10
    ashi
    0.10
     Yosh
    0.10
    oka
    0.09
    arty
    0.09
     wand
    0.09
    Japan
    0.09
    Activations Density 0.651%

    No Known Activations