© 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. 8580
    Prev
    Next
    INDEX
    Explanations

    family members' relationships

    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
     heads
    -0.08
     Guest
    -0.08
    Guest
    -0.08
     intr
    -0.07
     burg
    -0.07
     stations
    -0.07
    kee
    -0.07
     approved
    -0.07
     mouths
    -0.07
    PTY
    -0.07
    POSITIVE LOGITS
     twin
    0.13
     son
    0.12
     daughter
    0.12
     brother
    0.12
     siblings
    0.12
     family
    0.12
     sons
    0.11
     nephew
    0.11
     mother
    0.11
     father
    0.11
    Activations Density 0.256%

    No Known Activations