© 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. 8679
    Prev
    Next
    INDEX
    Explanations

    load a

    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
     Lov
    -0.09
     crumbs
    -0.08
    uten
    -0.08
     Quar
    -0.08
    ator
    -0.08
    :date
    -0.07
    ìĹ´
    -0.07
    activate
    -0.07
    ya
    -0.07
    gard
    -0.07
    POSITIVE LOGITS
    edly
    0.11
    rant
    0.11
    ings
    0.11
     Disqus
    0.10
    txt
    0.09
    ØŃ
    0.09
    mini
    0.09
    semblies
    0.09
    shed
    0.09
    rea
    0.09
    Activations Density 0.071%

    No Known Activations