© 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. 8716
    Prev
    Next
    INDEX
    Explanations

    to create/produce/get

    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
     anno
    -0.08
     lest
    -0.08
     satur
    -0.08
    tries
    -0.08
    otty
    -0.07
     participates
    -0.07
    lando
    -0.07
     beaut
    -0.07
     gad
    -0.07
    STD
    -0.07
    POSITIVE LOGITS
     indirectly
    0.12
     directly
    0.11
     sufficient
    0.10
    wal
    0.10
     accomplish
    0.10
     suff
    0.10
     Buckley
    0.09
     Enable
    0.09
     dr
    0.09
    KC
    0.09
    Activations Density 0.607%

    No Known Activations