© 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. 55074
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    oday
    -0.10
    ambi
    -0.09
    perfect
    -0.09
    thr
    -0.09
     totalement
    -0.09
    GIN
    -0.09
     realistically
    -0.09
    ilians
    -0.09
    means
    -0.09
    aly
    -0.08
    POSITIVE LOGITS
    Controls
    0.07
    .cms
    0.07
     Kl
    0.07
     Barg
    0.07
     Adrian
    0.07
     emerging
    0.07
    loom
    0.07
    Publisher
    0.07
     Arb
    0.07
    burger
    0.06
    Activations Density 0.003%

    No Known Activations