© 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. 58769
    Prev
    Next
    INDEX
    Explanations

    age before

    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
    র
    -0.09
    ampo
    -0.09
    /post
    -0.09
     domic
    -0.09
    ram
    -0.08
    anners
    -0.08
     RSS
    -0.08
     Purs
    -0.08
     Cho
    -0.08
     apprent
    -0.08
    POSITIVE LOGITS
     Vaughan
    0.09
    ios
    0.09
    uka
    0.09
    dims
    0.09
    .HTML
    0.09
     sle
    0.08
     silenced
    0.08
     nod
    0.08
    nod
    0.08
     rem
    0.08
    Activations Density 0.064%

    No Known Activations