© 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. 55103
    Prev
    Next
    INDEX
    Explanations

    user inputs or configuration

    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
    uter
    -0.09
    (sk
    -0.09
     connexion
    -0.09
     Kes
    -0.08
    sk
    -0.08
    hood
    -0.08
     Receipt
    -0.08
    /comment
    -0.08
    jon
    -0.08
    -es
    -0.08
    POSITIVE LOGITS
     dem
    0.09
    -selected
    0.09
     supply
    0.09
    ucci
    0.08
    -defined
    0.08
    uda
    0.08
     Bronx
    0.08
     supplied
    0.08
    bj
    0.08
    umi
    0.08
    Activations Density 0.070%

    No Known Activations