© 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. 54282
    Prev
    Next
    INDEX
    Explanations

    .com/.org paths

    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
     wast
    -0.08
     Gund
    -0.08
     troub
    -0.08
     Tucker
    -0.08
    æĬķ
    -0.07
     windows
    -0.07
     Ange
    -0.07
     Succ
    -0.07
     wasted
    -0.07
     working
    -0.07
    POSITIVE LOGITS
    pch
    0.10
     intact
    0.10
    uge
    0.09
    veillance
    0.09
     crunch
    0.09
     ph
    0.09
    pulse
    0.09
     Crunch
    0.09
    /MIT
    0.09
     redistributed
    0.09
    Activations Density 0.001%

    No Known Activations