© 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. 8758
    Prev
    Next
    INDEX
    Explanations

    lists of numbers or ages

    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
    sel
    -0.08
    ountains
    -0.08
     techn
    -0.08
     opt
    -0.08
    techn
    -0.08
    yne
    -0.08
    ottle
    -0.08
    Witness
    -0.08
     PROP
    -0.07
     nond
    -0.07
    POSITIVE LOGITS
    SY
    0.10
     Cro
    0.09
     lö
    0.09
    nis
    0.09
     Twelve
    0.09
     bé
    0.09
    ritt
    0.09
     Mode
    0.08
    ány
    0.08
    uria
    0.08
    Activations Density 0.056%

    No Known Activations