© 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. 61495
    Prev
    Next
    INDEX
    Explanations

    patent document 1

    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
     mand
    -0.09
    ë£
    -0.08
    abbo
    -0.08
    tog
    -0.08
    egas
    -0.08
    ria
    -0.08
    leep
    -0.08
    oday
    -0.08
     IID
    -0.08
    acc
    -0.08
    POSITIVE LOGITS
    ioni
    0.08
     configparser
    0.08
     Milton
    0.08
    anyl
    0.08
    thumbnail
    0.08
     паÑĢ
    0.08
     overst
    0.08
    ux
    0.08
     fizz
    0.08
    imas
    0.07
    Activations Density 0.001%

    No Known Activations