© 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. 53782
    Prev
    Next
    INDEX
    Explanations

    planning and design

    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
    erot
    -0.10
    ered
    -0.10
     abs
    -0.10
    oes
    -0.09
    .tk
    -0.09
     Abs
    -0.09
    otes
    -0.08
    /hooks
    -0.08
     monet
    -0.08
     timing
    -0.08
    POSITIVE LOGITS
     scratch
    0.09
    nya
    0.09
     Hamm
    0.08
    rez
    0.08
     swagger
    0.08
     strtoupper
    0.08
    алÑĮ
    0.07
    ysz
    0.07
     ense
    0.07
    perf
    0.07
    Activations Density 0.070%

    No Known Activations