© 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. 1155
    Prev
    Next
    INDEX
    Explanations

    young people and children

    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
     retiring
    -0.10
     retired
    -0.10
     retire
    -0.10
     Women
    -0.10
     women
    -0.10
     Husband
    -0.10
    Women
    -0.10
     retirement
    -0.10
    Woman
    -0.09
     Lect
    -0.09
    POSITIVE LOGITS
     boys
    0.17
     growing
    0.16
     classmates
    0.15
     inherited
    0.14
     boy
    0.14
     innocence
    0.14
     girls
    0.14
     Scouts
    0.13
     school
    0.13
     girl
    0.13
    Activations Density 2.004%

    No Known Activations