© 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. 8743
    Prev
    Next
    INDEX
    Explanations

    We followed by a verb representing action or finding

    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
    itta
    -0.09
    .ul
    -0.09
    klä
    -0.08
    bos
    -0.08
    .constructor
    -0.08
    gi
    -0.08
     NEED
    -0.08
    ëıĦ
    -0.08
     groom
    -0.08
    gow
    -0.08
    POSITIVE LOGITS
    cede
    0.09
    ¢
    0.09
    her
    0.09
     waits
    0.09
    agn
    0.08
     quits
    0.08
     Lies
    0.08
     Simone
    0.08
     speaks
    0.08
    thers
    0.08
    Activations Density 0.569%

    No Known Activations