© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    sqrt and equations

    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
     gran
    -0.08
    okin
    -0.07
    ém
    -0.07
    -up
    -0.07
     GIS
    -0.07
    FACT
    -0.07
    aset
    -0.07
     Bern
    -0.06
    stoff
    -0.06
     Companion
    -0.06
    POSITIVE LOGITS
    chy
    0.10
     Synd
    0.10
    ataka
    0.10
    avis
    0.09
    cin
    0.09
    odo
    0.09
    Tp
    0.09
    abar
    0.09
     sacks
    0.09
     Sullivan
    0.08
    Activations Density 0.057%

    No Known Activations