© 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. 61415
    Prev
    Next
    INDEX
    Explanations

    #define macros

    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
     Consortium
    -0.09
    blr
    -0.09
    ttp
    -0.09
     accommodating
    -0.09
    prech
    -0.09
    nection
    -0.09
     incor
    -0.08
    .saved
    -0.08
    aldi
    -0.08
     cle
    -0.08
    POSITIVE LOGITS
     Dud
    0.09
     similarly
    0.08
    ulp
    0.08
     casting
    0.08
     pill
    0.08
     Omn
    0.08
    ãĥ£
    0.07
    hor
    0.07
     Vog
    0.07
     Ott
    0.07
    Activations Density 0.004%

    No Known Activations