© 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. 61924
    Prev
    Next
    INDEX
    Explanations

    matrices or bases

    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
     entry
    -0.09
     Entry
    -0.09
     Briggs
    -0.08
     provisional
    -0.08
    rud
    -0.08
     Laure
    -0.08
     Stra
    -0.08
    kaar
    -0.08
    ucci
    -0.08
    erde
    -0.08
    POSITIVE LOGITS
    basis
    0.10
    clave
    0.09
    amps
    0.09
     BASIS
    0.09
    è¦
    0.08
    orest
    0.08
    iki
    0.08
     bases
    0.08
     Maid
    0.08
     Arist
    0.08
    Activations Density 0.033%

    No Known Activations