© 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. 54851
    Prev
    Next
    INDEX
    Explanations

    second consecutive

    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
     consistently
    -0.09
    aga
    -0.08
    tractor
    -0.08
     anywhere
    -0.08
     numerous
    -0.08
     brake
    -0.07
     dated
    -0.07
    à¥į
    -0.07
     aspir
    -0.07
    ced
    -0.07
    POSITIVE LOGITS
    auss
    0.10
     Tonight
    0.10
     cond
    0.09
    COND
    0.09
     Triumph
    0.09
    vous
    0.09
     Crowley
    0.09
    asha
    0.09
    ;base
    0.09
    imos
    0.09
    Activations Density 0.067%

    No Known Activations