© 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. 4442
    Prev
    Next
    INDEX
    Explanations

    tournament champions

    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
     Advantage
    -0.08
    Mais
    -0.08
     Straw
    -0.07
     Baum
    -0.07
     Treat
    -0.07
     complains
    -0.07
    antu
    -0.07
     Properties
    -0.07
    iid
    -0.07
     En
    -0.07
    POSITIVE LOGITS
    isto
    0.10
    sse
    0.10
    nev
    0.09
    415
    0.09
     yell
    0.09
    hani
    0.09
     unr
    0.09
    ANI
    0.09
    rose
    0.09
     Dann
    0.09
    Activations Density 0.391%

    No Known Activations