© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    eclipse followed by jface or org

    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
    Negative Logits
     contracting
    -0.09
    ARM
    -0.09
     Speaking
    -0.09
    obi
    -0.09
    ecs
    -0.09
    .ps
    -0.09
    -speaking
    -0.08
    aren
    -0.08
    stin
    -0.08
     speaking
    -0.08
    POSITIVE LOGITS
    usb
    0.09
    lung
    0.08
    ALA
    0.08
    cheon
    0.07
    lander
    0.07
     ide
    0.07
    .swt
    0.07
    utra
    0.07
     Oval
    0.07
     neg
    0.07
    Activations Density 0.004%

    No Known Activations