© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8649
    Prev
    Next
    INDEX
    Explanations

    past tense temporal phrases

    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
    Negative Logits
     expire
    -0.08
     finally
    -0.07
     DE
    -0.06
     unexpectedly
    -0.06
    until
    -0.06
     until
    -0.06
     вÑĢем
    -0.06
     ret
    -0.06
    DE
    -0.06
    ãĥ©ãĥ³
    -0.06
    POSITIVE LOGITS
    compare
    0.12
     irony
    0.11
     scarcity
    0.11
     compares
    0.11
    ucci
    0.11
     scarce
    0.11
    emo
    0.11
    slaught
    0.11
     Compare
    0.11
    imei
    0.11
    Activations Density 0.205%

    No Known Activations