© 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. 58926
    Prev
    Next
    INDEX
    Explanations

    Android `.` or code symbols

    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
     banc
    -0.10
     Jared
    -0.10
    asu
    -0.09
    asse
    -0.09
     Grocery
    -0.09
    };č↵č↵č↵
    -0.09
    quer
    -0.08
    enger
    -0.08
     Berkshire
    -0.08
     *_
    -0.08
    POSITIVE LOGITS
     Mojo
    0.08
     Hol
    0.08
    illet
    0.08
    ACES
    0.07
     surg
    0.07
    Gateway
    0.07
    ROP
    0.07
     ={↵
    0.07
    itz
    0.07
    illes
    0.07
    Activations Density 0.001%

    No Known Activations