© 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. 61676
    Prev
    Next
    INDEX
    Explanations

    custom actions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ean
    -0.09
     assured
    -0.09
    oned
    -0.09
    ÑĢаÐ
    -0.09
    iev
    -0.08
     churn
    -0.08
    ens
    -0.08
    autos
    -0.08
    ego
    -0.08
     HIGH
    -0.08
    POSITIVE LOGITS
    (acc
    0.10
    ced
    0.10
     Sasha
    0.09
    avorite
    0.09
    ccount
    0.09
    -ID
    0.09
     menn
    0.08
     clickable
    0.08
    ulfill
    0.08
    (#)
    0.08
    Activations Density 0.003%

    No Known Activations