© 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. 58823
    Prev
    Next
    INDEX
    Explanations

    code constructs following parentheses

    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
    Deprecated
    -0.07
    itzer
    -0.07
     closets
    -0.07
     Prelude
    -0.06
    èĹı
    -0.06
     Pist
    -0.06
     met
    -0.06
     closet
    -0.06
    ears
    -0.06
    pants
    -0.06
    POSITIVE LOGITS
    ogan
    0.10
    ripp
    0.10
     boo
    0.10
    Friendly
    0.10
    shire
    0.10
    Longrightarrow
    0.09
    unate
    0.09
    emain
    0.09
    elim
    0.09
     crunch
    0.09
    Activations Density 0.001%

    No Known Activations