© 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. 8674
    Prev
    Next
    INDEX
    Explanations

    institutions and addresses

    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
    iko
    -0.13
    pcl
    -0.12
    opl
    -0.11
     clearfix
    -0.11
    /im
    -0.11
    /mark
    -0.11
    styl
    -0.11
    alley
    -0.11
     marketed
    -0.11
    cla
    -0.11
    POSITIVE LOGITS
    iked
    0.06
     punched
    0.06
     Institution
    0.05
    tics
    0.05
    FA
    0.05
    579
    0.05
     punch
    0.05
     Buff
    0.05
     Exc
    0.05
     bootstrap
    0.05
    Activations Density 0.033%

    No Known Activations