© 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. 61167
    Prev
    Next
    INDEX
    Explanations

    ocarditis, ocardial, ocardium

    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
    orig
    -0.10
     Pace
    -0.10
    еÑģÑĮ
    -0.10
    o
    -0.09
    omat
    -0.09
    aton
    -0.09
    atro
    -0.09
    ares
    -0.09
     condom
    -0.08
     Norris
    -0.08
    POSITIVE LOGITS
    itis
    0.09
    edef
    0.08
    æ¼
    0.08
    enty
    0.08
    ucci
    0.07
    das
    0.07
     designate
    0.07
    /fa
    0.07
    mal
    0.07
     precise
    0.07
    Activations Density 0.001%

    No Known Activations