© 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. 61429
    Prev
    Next
    INDEX
    Explanations

    "as [noun]" or "of [noun]"

    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
    .myapplication
    -0.11
    ).(
    -0.10
     ther
    -0.10
     '=
    -0.09
     famous
    -0.09
     Ther
    -0.09
     ()č↵
    -0.09
    Âł↵
    -0.09
    ³³³³³³³
    -0.09
    ...(
    -0.09
    POSITIVE LOGITS
    åı°
    0.08
     guarded
    0.08
     rij
    0.08
    ksi
    0.07
    illi
    0.07
     Forbidden
    0.07
     rider
    0.07
     bub
    0.07
    UIL
    0.07
    -register
    0.07
    Activations Density 0.229%

    No Known Activations