© 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. 61916
    Prev
    Next
    INDEX
    Explanations

    quoted phrases and terms

    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
     neglig
    -0.08
    idge
    -0.07
     tr
    -0.07
     Entire
    -0.07
     medic
    -0.07
     Viet
    -0.07
     siz
    -0.07
     stiff
    -0.07
     disproportion
    -0.06
    tie
    -0.06
    POSITIVE LOGITS
     Dich
    0.11
    .gc
    0.11
     dich
    0.10
    WARD
    0.10
    unta
    0.10
    ulp
    0.10
    .dynamic
    0.10
    .sd
    0.10
     ìŀħ
    0.09
    uil
    0.09
    Activations Density 0.001%

    No Known Activations