© 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. 8688
    Prev
    Next
    INDEX
    Explanations

    groundwork, foundation, paving the way

    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
    eli
    -0.09
     Wah
    -0.09
     Telescope
    -0.08
    -Ta
    -0.08
    zik
    -0.08
     dall
    -0.08
     duk
    -0.07
    pager
    -0.07
     Stake
    -0.07
    188
    -0.07
    POSITIVE LOGITS
     groundwork
    0.14
     pave
    0.12
     foundation
    0.10
     paving
    0.10
     launching
    0.09
    ä¿
    0.09
     launch
    0.09
     stepping
    0.09
    permission
    0.09
    future
    0.09
    Activations Density 0.275%

    No Known Activations