© 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. 8734
    Prev
    Next
    INDEX
    Explanations

    duo or pair

    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
     dec
    -0.08
     ta
    -0.07
    unic
    -0.07
     detach
    -0.07
    CAS
    -0.07
    ä»ĭ
    -0.07
    illis
    -0.07
    åº
    -0.07
     sal
    -0.07
     detached
    -0.07
    POSITIVE LOGITS
     pair
    0.27
     pairs
    0.25
    _pair
    0.23
     pairwise
    0.23
    Pair
    0.22
     Pair
    0.22
    pair
    0.20
    pairs
    0.17
     duo
    0.17
    Pairs
    0.17
    Activations Density 0.732%

    No Known Activations