© 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. 8942
    Prev
    Next
    INDEX
    Explanations

    version, group, or episode numbering

    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
    (s
    -0.10
    ff
    -0.09
    oin
    -0.09
     Pret
    -0.07
    leigh
    -0.07
     midway
    -0.07
    pec
    -0.07
     seri
    -0.07
     Punch
    -0.07
    ges
    -0.07
    POSITIVE LOGITS
    enus
    0.10
     Dodd
    0.10
    epam
    0.10
     Burst
    0.09
    olley
    0.09
    IPA
    0.09
    orest
    0.09
    726
    0.09
    onica
    0.09
    oti
    0.09
    Activations Density 0.192%

    No Known Activations