© 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. 8790
    Prev
    Next
    INDEX
    Explanations

    component parts

    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
    ivy
    -0.09
     spokesperson
    -0.08
    erty
    -0.08
    .digital
    -0.07
    -input
    -0.07
    orda
    -0.07
    yang
    -0.07
    ær
    -0.07
     Infinity
    -0.07
     graph
    -0.07
    POSITIVE LOGITS
     Bene
    0.10
    OTT
    0.09
     crossings
    0.09
     crossed
    0.09
     Numerous
    0.09
    Unsupported
    0.09
     soften
    0.08
     plenty
    0.08
     deserve
    0.08
    DES
    0.08
    Activations Density 0.165%

    No Known Activations