© 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. 3562
    Prev
    Next
    INDEX
    Explanations

    choosing between options

    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
     Tal
    -0.09
     coordinate
    -0.09
    Organization
    -0.09
    assage
    -0.09
     tal
    -0.08
     Baron
    -0.08
     trace
    -0.08
    neh
    -0.08
     зап
    -0.08
     intercept
    -0.08
    POSITIVE LOGITS
     Choosing
    0.21
     choice
    0.20
     choosing
    0.20
     decision
    0.20
     choices
    0.19
    Choosing
    0.18
     Choice
    0.17
     decisions
    0.17
     Decision
    0.17
     Choices
    0.17
    Activations Density 0.424%

    No Known Activations