© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1522
    Prev
    Next
    INDEX
    Explanations

    High School names and locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    chten
    -0.11
    ebin
    -0.10
    ULE
    -0.10
     Facilities
    -0.10
    /cart
    -0.10
    alyzer
    -0.10
     Bulls
    -0.09
     Sold
    -0.09
    yz
    -0.09
    isode
    -0.09
    POSITIVE LOGITS
     University
    0.08
    -class
    0.08
     Publishing
    0.08
    inston
    0.08
     Hospital
    0.08
     Group
    0.08
     Express
    0.08
     Downs
    0.08
    Ñģк
    0.08
     Herc
    0.08
    Activations Density 2.698%

    No Known Activations