© 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. 56595
    Prev
    Next
    INDEX
    Explanations

    settlement, budget, or deal

    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
    (est
    -0.08
    ASP
    -0.08
     hopes
    -0.08
    st
    -0.08
    lv
    -0.08
     estimate
    -0.08
     toward
    -0.08
     term
    -0.08
    bid
    -0.07
     expect
    -0.07
    POSITIVE LOGITS
    eler
    0.10
    oge
    0.09
    iales
    0.09
    etics
    0.09
    sm
    0.09
     rew
    0.09
     desper
    0.09
    aires
    0.09
     vere
    0.08
    ır
    0.08
    Activations Density 0.019%

    No Known Activations