© 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. 8174
    Prev
    Next
    INDEX
    Explanations

    presenting something

    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
    ders
    -0.11
    dent
    -0.10
    nce
    -0.10
     Restr
    -0.09
    ceans
    -0.09
    ials
    -0.09
    neau
    -0.09
     /^(
    -0.09
    945
    -0.09
     prise
    -0.09
    POSITIVE LOGITS
    uger
    0.09
    isms
    0.08
    ug
    0.08
    éĿ¢
    0.07
    appa
    0.07
    ism
    0.07
    adem
    0.07
     arg
    0.07
    ICAL
    0.07
    ÃŃm
    0.07
    Activations Density 0.046%

    No Known Activations