© 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. 58757
    Prev
    Next
    INDEX
    Explanations

    deterioration

    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
    ical
    -0.11
    nel
    -0.10
    ness
    -0.09
    sto
    -0.09
    atica
    -0.09
    atic
    -0.09
     indent
    -0.09
    less
    -0.09
    -uri
    -0.08
    richt
    -0.08
    POSITIVE LOGITS
    er
    0.10
    =UTF
    0.09
    rov
    0.09
    oe
    0.08
    kad
    0.08
    vik
    0.08
    _PROJECT
    0.08
     dum
    0.08
     mental
    0.08
    verts
    0.08
    Activations Density 0.002%

    No Known Activations