© 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. 4110
    Prev
    Next
    INDEX
    Explanations

    leptons, masses, gauge, charges

    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
     illuminated
    -0.10
    nga
    -0.09
     Dead
    -0.09
     slur
    -0.09
    verb
    -0.09
     optical
    -0.09
     sampled
    -0.09
     visual
    -0.09
     hourly
    -0.09
    %%
    -0.08
    POSITIVE LOGITS
     Venez
    0.10
     cosm
    0.10
     Pierce
    0.10
     inherited
    0.09
     vacuum
    0.09
     charges
    0.09
     charged
    0.08
     gauge
    0.08
     inheritance
    0.08
     lept
    0.08
    Activations Density 0.044%

    No Known Activations