© 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. 3763
    Prev
    Next
    INDEX
    Explanations

    an/the describing noun

    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
    aminer
    -0.11
     rais
    -0.10
    REAM
    -0.10
    hone
    -0.10
    atin
    -0.10
    apos
    -0.10
    .backward
    -0.09
    inz
    -0.09
    Splash
    -0.09
     Pru
    -0.09
    POSITIVE LOGITS
     target
    0.13
    target
    0.09
     input
    0.09
    _target
    0.07
     demean
    0.07
    oge
    0.07
     subject
    0.07
     Armstrong
    0.07
    iglia
    0.07
    lander
    0.06
    Activations Density 0.273%

    No Known Activations