© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 77
    Prev
    Next
    INDEX
    Explanations

    appeal from a

    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
    rawer
    -0.10
     wherever
    -0.10
    лÑĮ
    -0.10
    oS
    -0.10
     adj
    -0.10
    (any
    -0.10
    bdb
    -0.09
    пп
    -0.09
    ugin
    -0.09
    adol
    -0.09
    POSITIVE LOGITS
     allegedly
    0.08
     purported
    0.08
     urb
    0.08
     nineteen
    0.08
     admittedly
    0.08
     spectacular
    0.07
     Epic
    0.07
     alleged
    0.07
    formerly
    0.07
     sixteen
    0.07
    Activations Density 1.271%

    No Known Activations