© 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. 58917
    Prev
    Next
    INDEX
    Explanations

    . nature citation

    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
     lenses
    -0.07
     draw
    -0.07
     scour
    -0.07
    oup
    -0.07
     drew
    -0.06
     leverage
    -0.06
     NEWS
    -0.06
    VR
    -0.06
     hom
    -0.06
    azel
    -0.06
    POSITIVE LOGITS
    aad
    0.12
    wagon
    0.11
    ikon
    0.11
    ULK
    0.11
    INVALID
    0.10
     Vac
    0.10
     appropri
    0.10
    agos
    0.10
    ween
    0.10
    alem
    0.10
    Activations Density 0.006%

    No Known Activations