© 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. 8290
    Prev
    Next
    INDEX
    Explanations

    a word followed by a noun or specifier

    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
     Comp
    -0.13
     Su
    -0.12
     Brend
    -0.12
    cka
    -0.12
     LOT
    -0.12
    arend
    -0.12
    "text
    -0.11
    bins
    -0.11
    ampil
    -0.11
    Comp
    -0.11
    POSITIVE LOGITS
    gle
    0.05
    ets
    0.05
     echt
    0.04
    inders
    0.04
     Pool
    0.04
     Skinner
    0.04
    endar
    0.04
     Goldberg
    0.04
     mingle
    0.04
     UNICODE
    0.04
    Activations Density 0.907%

    No Known Activations