© 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. 56644
    Prev
    Next
    INDEX
    Explanations

    noise pollution

    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
     go
    -0.09
    &C
    -0.08
     Cler
    -0.08
     pur
    -0.08
    hart
    -0.08
     resolution
    -0.08
     Mor
    -0.08
    onen
    -0.08
     Bran
    -0.08
    .EVT
    -0.08
    POSITIVE LOGITS
     allot
    0.08
    fty
    0.08
    ornment
    0.08
    egment
    0.08
     Positioned
    0.08
     unle
    0.08
    derabad
    0.08
    assage
    0.08
    ucha
    0.08
     Revenge
    0.08
    Activations Density 0.007%

    No Known Activations