© 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. 61807
    Prev
    Next
    INDEX
    Explanations

    coding arguments or variables

    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
    isy
    -0.12
    ideshow
    -0.12
     &:
    -0.12
    Ĺı
    -0.12
    isos
    -0.12
     Wis
    -0.11
    )new
    -0.11
    indy
    -0.11
    feito
    -0.11
    û
    -0.11
    POSITIVE LOGITS
     Dess
    0.07
    eland
    0.07
     commercial
    0.06
     merit
    0.06
     rem
    0.06
     Tort
    0.06
     commercially
    0.05
     Dough
    0.05
    eldon
    0.05
    -
    0.05
    Activations Density 0.008%

    No Known Activations