© 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. 8707
    Prev
    Next
    INDEX
    Explanations

    stream, communication, season, ad, ucha, raf, eter, apparatus

    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
    <|fim_middle|>
    -0.08
     Gavin
    -0.07
    eks
    -0.07
     redeemed
    -0.07
     apprec
    -0.07
     Fro
    -0.07
     imag
    -0.06
     Tul
    -0.06
     Archer
    -0.06
    intro
    -0.06
    POSITIVE LOGITS
    prot
    0.10
    metis
    0.09
    urre
    0.09
     civil
    0.09
    getter
    0.09
    ãĤģ
    0.09
    uong
    0.09
    Soup
    0.09
     GOODMAN
    0.09
    istogram
    0.09
    Activations Density 0.191%

    No Known Activations