© 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. 8751
    Prev
    Next
    INDEX
    Explanations

    National Laboratory

    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
     Platz
    -0.09
     apparent
    -0.08
    åİ
    -0.08
     Fargo
    -0.08
    _async
    -0.08
     Side
    -0.08
    代
    -0.08
     attent
    -0.07
     gre
    -0.07
     Ut
    -0.07
    POSITIVE LOGITS
    .CreateInstance
    0.10
    amiento
    0.09
     imper
    0.09
    -bold
    0.09
    ypse
    0.09
    ollo
    0.09
    /details
    0.08
     spons
    0.08
    olean
    0.08
    wap
    0.08
    Activations Density 2.856%

    No Known Activations