© 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. 53767
    Prev
    Next
    INDEX
    Explanations

    guys jacket

    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
     admir
    -0.09
    cta
    -0.09
    emption
    -0.09
     quot
    -0.09
    abl
    -0.09
    anned
    -0.09
    dup
    -0.09
     fir
    -0.09
    .Title
    -0.09
    yleft
    -0.09
    POSITIVE LOGITS
     orderly
    0.09
    aine
    0.08
     dough
    0.08
    åħ
    0.08
    ↵↵↵↵
    0.08
     Appeal
    0.07
     reduced
    0.07
    ↵↵
    0.07
    sus
    0.07
    Å¡e
    0.07
    Activations Density 0.001%

    No Known Activations