© 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. 58713
    Prev
    Next
    INDEX
    Explanations

    clinic or downloaded titles

    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
     sometimes
    -0.08
     Sylv
    -0.08
     Fran
    -0.07
    utra
    -0.07
     Finger
    -0.07
    MSN
    -0.07
    zl
    -0.07
    orca
    -0.07
     Schneider
    -0.07
     stalled
    -0.07
    POSITIVE LOGITS
    /title
    0.11
     Tib
    0.10
    indr
    0.09
    à¹ĩ
    0.09
     Mund
    0.09
     refute
    0.09
    kal
    0.09
    counter
    0.09
    -road
    0.09
     Heg
    0.09
    Activations Density 0.110%

    No Known Activations