© 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. 3181
    Prev
    Next
    INDEX
    Explanations

    name origin

    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
     spelled
    -0.11
     synonym
    -0.11
    hei
    -0.10
    sein
    -0.09
    stress
    -0.09
     synonymous
    -0.09
     pronounce
    -0.09
     namespace
    -0.09
    Į¨
    -0.09
     acronym
    -0.08
    POSITIVE LOGITS
    -account
    0.10
    pring
    0.08
    aly
    0.08
     account
    0.08
    ails
    0.08
    ippi
    0.08
     Contents
    0.07
    metics
    0.07
    Contents
    0.07
    iec
    0.07
    Activations Density 0.222%

    No Known Activations