© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1205
    Prev
    Next
    INDEX
    Explanations

    /item?id

    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
     overl
    -0.08
     "[
    -0.08
    oter
    -0.07
     guarding
    -0.07
     nearby
    -0.07
    wo
    -0.07
     "...
    -0.07
     sc
    -0.06
    ÃĦ
    -0.06
     Burr
    -0.06
    POSITIVE LOGITS
     ance
    0.10
    malink
    0.10
    azor
    0.10
    isplay
    0.10
    /Input
    0.10
     Lifetime
    0.09
    outu
    0.09
    poons
    0.09
     hott
    0.09
    aison
    0.09
    Activations Density 0.484%

    No Known Activations