© 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. 53744
    Prev
    Next
    INDEX
    Explanations

    PostgreSQL database

    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
    ¶
    -0.10
     incompet
    -0.09
    ain
    -0.09
     pot
    -0.08
     tie
    -0.08
    /no
    -0.08
    estate
    -0.08
     Lone
    -0.08
     langs
    -0.08
     Tie
    -0.08
    POSITIVE LOGITS
     falsely
    0.10
    ież
    0.09
     Ned
    0.09
     Tri
    0.09
     sending
    0.09
    uga
    0.09
     repetition
    0.08
    _ps
    0.08
     div
    0.08
     tri
    0.08
    Activations Density 0.076%

    No Known Activations