© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    projects and businesses

    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
    .rem
    -0.09
     Moor
    -0.08
     Neo
    -0.08
    Locator
    -0.08
    .quant
    -0.08
    uit
    -0.08
    oad
    -0.08
    /actions
    -0.08
    LEV
    -0.08
    Cheap
    -0.08
    POSITIVE LOGITS
     fled
    0.11
     projects
    0.11
    "č↵č↵č↵
    0.09
     alongside
    0.09
     underst
    0.09
     client
    0.09
     Projects
    0.09
    rray
    0.09
     ata
    0.08
     facult
    0.08
    Activations Density 0.386%

    No Known Activations