© 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. 8076
    Prev
    Next
    INDEX
    Explanations

    javascript libraries

    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
     hud
    -0.12
    hee
    -0.11
    iens
    -0.10
    oru
    -0.10
    iams
    -0.09
    TD
    -0.09
    lush
    -0.09
    >((
    -0.09
    //===
    -0.09
    adt
    -0.09
    POSITIVE LOGITS
     Sym
    0.08
    KEN
    0.08
     McKenzie
    0.07
     zest
    0.07
     Materials
    0.07
    zo
    0.07
    apt
    0.07
    ecc
    0.07
     neu
    0.07
     Kend
    0.07
    Activations Density 0.001%

    No Known Activations