© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1238
    Prev
    Next
    INDEX
    Explanations

    stars, galaxies, and space

    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
     Iv
    -0.08
     Bates
    -0.08
     Pam
    -0.08
    ibility
    -0.07
    adow
    -0.07
    );;↵
    -0.07
    aton
    -0.07
     Pik
    -0.07
     Mirage
    -0.07
     grate
    -0.07
    POSITIVE LOGITS
    /star
    0.19
     star
    0.13
     astronomers
    0.12
     stars
    0.12
    ved
    0.12
    stellar
    0.12
     stellar
    0.12
     dust
    0.12
     orbit
    0.11
    -star
    0.11
    Activations Density 1.069%

    No Known Activations