© 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. 61295
    Prev
    Next
    INDEX
    Explanations

    mock interview, fake advert, staged event

    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
    olor
    -0.11
     Gat
    -0.11
     Clamp
    -0.10
     Furn
    -0.10
     Tough
    -0.10
    clar
    -0.10
    portrait
    -0.10
     uphill
    -0.09
    aggio
    -0.09
     saints
    -0.09
    POSITIVE LOGITS
     mock
    0.11
     mim
    0.08
     fake
    0.08
    iek
    0.08
     mimic
    0.07
     inferred
    0.07
     rejection
    0.07
     resembling
    0.07
     purported
    0.07
     blood
    0.07
    Activations Density 0.079%

    No Known Activations