© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by equals sign

    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
    anches
    -0.10
    icom
    -0.10
    (;
    -0.10
    eki
    -0.10
    .getLogger
    -0.09
    inder
    -0.09
    yles
    -0.09
    ArrayType
    -0.09
    rim
    -0.09
     Carn
    -0.09
    POSITIVE LOGITS
     Whitney
    0.08
     ay
    0.06
     Chop
    0.06
     Tubes
    0.06
     besides
    0.06
    .Never
    0.06
    OUNCE
    0.06
    sponsor
    0.06
     defined
    0.06
    rium
    0.06
    Activations Density 0.208%

    No Known Activations