© 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. 61279
    Prev
    Next
    INDEX
    Explanations

    is a / is an / is not

    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
    qua
    -0.10
    ses
    -0.09
     Whale
    -0.09
     aup
    -0.08
     pocket
    -0.08
    ook
    -0.08
     inset
    -0.08
     Spartan
    -0.07
     sleeve
    -0.07
     expect
    -0.07
    POSITIVE LOGITS
     berg
    0.10
    ruby
    0.09
    oil
    0.09
     Nunes
    0.09
    ueil
    0.09
     arguably
    0.09
     Berg
    0.09
     Archived
    0.08
    Unity
    0.08
    !=(
    0.08
    Activations Density 0.049%

    No Known Activations