© 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. 55280
    Prev
    Next
    INDEX
    Explanations

    leaving the eu

    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
     roundup
    -0.09
     overdue
    -0.08
     wax
    -0.08
    -us
    -0.08
     coincidence
    -0.08
    illos
    -0.08
     stim
    -0.08
     ROT
    -0.08
     crit
    -0.08
     scal
    -0.07
    POSITIVE LOGITS
     Brexit
    0.14
     renegot
    0.11
     Exiting
    0.11
     exiting
    0.10
    passport
    0.10
     separation
    0.10
     dissolution
    0.10
    hesion
    0.10
     severed
    0.10
     existential
    0.10
    Activations Density 0.025%

    No Known Activations