© 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. 8860
    Prev
    Next
    INDEX
    Explanations

    numbers followed by lists or enumerations

    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
     numerous
    -0.11
    -many
    -0.10
     many
    -0.09
     Numerous
    -0.09
     dozens
    -0.09
    ج
    -0.09
     Carolyn
    -0.09
     scam
    -0.08
    abor
    -0.08
    allen
    -0.08
    POSITIVE LOGITS
    ","","
    0.15
    ?,?,
    0.13
    ','','
    0.10
    umbed
    0.10
    NU
    0.09
    kor
    0.09
    ------+
    0.09
     dispar
    0.08
     ?,
    0.08
    roid
    0.08
    Activations Density 0.237%

    No Known Activations