© 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. 62013
    Prev
    Next
    INDEX
    Explanations

    numbers in ranges

    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
    Ľ
    -0.08
    ãĥĥ
    -0.07
     Gian
    -0.07
    sher
    -0.07
     Burk
    -0.07
    ãĥ¼ãĤ¸
    -0.07
     Kaplan
    -0.06
     deserved
    -0.06
     Destruction
    -0.06
    mania
    -0.06
    POSITIVE LOGITS
    andre
    0.10
    holm
    0.10
    ->↵
    0.10
     withd
    0.10
    olon
    0.10
    ';↵↵↵↵
    0.10
    .modules
    0.10
    engl
    0.10
    rais
    0.10
     predecess
    0.10
    Activations Density 0.066%

    No Known Activations