© 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. 4828
    Prev
    Next
    INDEX
    Explanations

    looking for something

    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
    aken
    -0.09
     Misc
    -0.08
    iente
    -0.08
    ãĥ¥
    -0.07
     Census
    -0.07
    iffs
    -0.07
    iple
    -0.07
     detections
    -0.07
     kindly
    -0.07
    -dist
    -0.07
    POSITIVE LOGITS
     elusive
    0.15
     elsewhere
    0.11
     urgently
    0.11
     desperately
    0.11
     lost
    0.10
    lost
    0.09
     suitable
    0.09
     buried
    0.09
     amid
    0.09
     unsuccessfully
    0.09
    Activations Density 0.407%

    No Known Activations