© 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. 2718
    Prev
    Next
    INDEX
    Explanations

    script src paths

    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
    upt
    -0.11
    emd
    -0.10
    rig
    -0.10
     &:
    -0.10
    ł
    -0.10
    spath
    -0.10
    icht
    -0.10
     bev
    -0.10
    apg
    -0.10
    .ravel
    -0.10
    POSITIVE LOGITS
    models
    0.08
     spot
    0.07
     models
    0.07
     diam
    0.07
    zeug
    0.07
    ifu
    0.07
    aira
    0.06
    igaret
    0.06
     Classic
    0.06
     Gam
    0.06
    Activations Density 0.019%

    No Known Activations