© 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. 5027
    Prev
    Next
    INDEX
    Explanations

    .value 2, prop 2

    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
    adero
    -0.10
    .stamp
    -0.09
     naturally
    -0.09
     Reform
    -0.09
    uary
    -0.09
     Dunk
    -0.09
    astr
    -0.09
    urf
    -0.09
    (TypeError
    -0.09
    apel
    -0.09
    POSITIVE LOGITS
    sta
    0.09
    iena
    0.08
     larg
    0.07
     Tango
    0.07
    -vertical
    0.07
    gn
    0.07
     replay
    0.07
    rek
    0.07
     programm
    0.07
     fam
    0.07
    Activations Density 0.112%

    No Known Activations