© 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. 61250
    Prev
    Next
    INDEX
    Explanations

    disappear, appeared, disappearance

    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
     vigil
    -0.09
    ador
    -0.09
    fruit
    -0.09
     unre
    -0.09
     hire
    -0.09
    serie
    -0.09
    ru
    -0.09
     Hire
    -0.09
    ted
    -0.09
    arf
    -0.08
    POSITIVE LOGITS
    ly
    0.11
    ingly
    0.09
    ances
    0.08
    agram
    0.08
    ages
    0.08
    ion
    0.08
    tron
    0.08
    TRA
    0.08
     Burton
    0.08
    acer
    0.07
    Activations Density 0.006%

    No Known Activations