© 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. 58837
    Prev
    Next
    INDEX
    Explanations

    .com/

    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
    #region
    -0.09
    ADVERTISEMENT
    -0.09
    -minded
    -0.09
     covered
    -0.09
    rut
    -0.09
     Honest
    -0.08
    Represent
    -0.08
    ören
    -0.08
     Solic
    -0.08
    .quote
    -0.08
    POSITIVE LOGITS
    fal
    0.09
    rale
    0.09
     Keller
    0.08
    burgh
    0.08
     parl
    0.08
     cock
    0.07
    rox
    0.07
    pector
    0.07
     Flat
    0.07
    orea
    0.07
    Activations Density 0.009%

    No Known Activations