© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    calling functions or methods

    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
    tas
    -0.08
     Gong
    -0.08
    eny
    -0.08
     Heavenly
    -0.08
     sustain
    -0.08
    ys
    -0.08
    Chance
    -0.07
     (`
    -0.07
     lap
    -0.07
    cle
    -0.07
    POSITIVE LOGITS
     automáticamente
    0.09
     flooded
    0.09
     gor
    0.09
    captures
    0.09
    pper
    0.09
     memor
    0.09
    OLUM
    0.09
    imon
    0.08
    orama
    0.08
    rans
    0.08
    Activations Density 0.633%

    No Known Activations