© 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. 4571
    Prev
    Next
    INDEX
    Explanations

    boolean true/false evaluation

    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
    Berry
    -0.08
    ties
    -0.08
     forever
    -0.08
     unt
    -0.08
     upside
    -0.08
    mont
    -0.08
     ta
    -0.08
    å£
    -0.08
    بر
    -0.08
    wei
    -0.07
    POSITIVE LOGITS
    ebb
    0.11
    azio
    0.10
    tright
    0.10
    ulton
    0.09
    eo
    0.09
    AREN
    0.08
    apa
    0.08
    pps
    0.08
    ;;↵↵
    0.08
    dden
    0.08
    Activations Density 0.008%

    No Known Activations