© 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. 54546
    Prev
    Next
    INDEX
    Explanations

    meta tags (date/author/content)

    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
    shi
    -0.10
    ÛĮر
    -0.10
    -highlight
    -0.10
    etag
    -0.09
    uye
    -0.09
    lig
    -0.09
     Hills
    -0.09
    cce
    -0.09
    thead
    -0.09
     Jobs
    -0.09
    POSITIVE LOGITS
    pect
    0.08
     frozen
    0.08
    Dest
    0.08
     nec
    0.08
     Lei
    0.07
     portal
    0.07
    ocaly
    0.07
    arth
    0.07
    Portal
    0.07
     convention
    0.06
    Activations Density 0.013%

    No Known Activations