© 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. 8672
    Prev
    Next
    INDEX
    Explanations

    batch processing

    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
    arend
    -0.10
     Seas
    -0.08
    iya
    -0.08
     sequ
    -0.08
    èĹı
    -0.08
     terminal
    -0.07
     rivals
    -0.07
     Memor
    -0.07
    (vars
    -0.07
     variables
    -0.07
    POSITIVE LOGITS
     batches
    0.16
     batch
    0.14
     Thousands
    0.14
    Batch
    0.14
     Batch
    0.14
     thousands
    0.14
    _batch
    0.13
    leet
    0.13
    Thousands
    0.12
     individual
    0.12
    Activations Density 0.760%

    No Known Activations