© 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. 53814
    Prev
    Next
    INDEX
    Explanations

    progress, technique, folders, drugs, buildings, data, material

    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
     crypt
    -0.10
    apons
    -0.10
    .Hash
    -0.10
    ika
    -0.10
     weave
    -0.09
    itr
    -0.09
    Crypt
    -0.09
    ayan
    -0.09
    uka
    -0.09
    awi
    -0.08
    POSITIVE LOGITS
     ÑĩеÑĢ
    0.08
    zan
    0.07
     Banner
    0.07
     Musk
    0.07
    CCCCCC
    0.07
    tra
    0.07
    mall
    0.07
     pur
    0.07
    ILLS
    0.06
    IOS
    0.06
    Activations Density 0.129%

    No Known Activations