© 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. 3514
    Prev
    Next
    INDEX
    Explanations

    AF_ and SYS_ prefixes

    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
    Tonight
    -0.09
    eted
    -0.08
    ness
    -0.08
    Ģ
    -0.08
     sight
    -0.08
     tonight
    -0.08
     fab
    -0.08
    Tiny
    -0.07
     sole
    -0.07
    edium
    -0.07
    POSITIVE LOGITS
    acha
    0.09
     selectable
    0.09
     stub
    0.09
    );"
    0.08
    iling
    0.08
     deleg
    0.08
    "_
    0.08
    atto
    0.08
    .Char
    0.07
    ivot
    0.07
    Activations Density 0.028%

    No Known Activations