© 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. 55051
    Prev
    Next
    INDEX
    Explanations

    fill color or attribute

    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
    (PHP
    -0.10
    upt
    -0.10
    furt
    -0.09
     Theft
    -0.09
    zug
    -0.09
    zas
    -0.09
     lent
    -0.08
    agraph
    -0.08
    -low
    -0.08
    noch
    -0.08
    POSITIVE LOGITS
    ively
    0.09
    /tab
    0.08
     Nested
    0.07
    CY
    0.07
     CY
    0.07
     favor
    0.07
     Barber
    0.07
    friend
    0.07
     nowhere
    0.07
     verde
    0.07
    Activations Density 0.003%

    No Known Activations