© 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. 57574
    Prev
    Next
    INDEX
    Explanations

    INTRODUCTION

    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
     Lim
    -0.10
    vere
    -0.09
     Nep
    -0.09
     Clim
    -0.08
    revision
    -0.08
     Restoration
    -0.08
    leen
    -0.08
     waypoint
    -0.08
    /logger
    -0.08
    otas
    -0.08
    POSITIVE LOGITS
     Introduction
    0.12
    ASF
    0.11
     introduction
    0.11
    Introduction
    0.10
     screened
    0.09
    anford
    0.09
     IBM
    0.08
     nor
    0.08
     PEN
    0.08
     Penny
    0.08
    Activations Density 0.018%

    No Known Activations