© 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. 58121
    Prev
    Next
    INDEX
    Explanations

    information on

    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
     explanation
    -0.10
     description
    -0.09
     advice
    -0.09
     summary
    -0.08
     discussion
    -0.08
     estimates
    -0.08
     details
    -0.08
     example
    -0.08
    seg
    -0.08
     overs
    -0.08
    POSITIVE LOGITS
    Challenge
    0.09
    181
    0.09
     mies
    0.09
     Cowboy
    0.09
     Shock
    0.09
     plano
    0.09
    .mysql
    0.09
     Challenge
    0.08
    mes
    0.08
    ankind
    0.08
    Activations Density 0.059%

    No Known Activations