© 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. 4944
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or delimiters

    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
     freed
    -0.08
     Urs
    -0.08
    osh
    -0.07
     challenged
    -0.07
    vic
    -0.07
     Din
    -0.07
     Ros
    -0.07
    ven
    -0.07
    oni
    -0.07
    ands
    -0.07
    POSITIVE LOGITS
     Highlands
    0.09
    UGE
    0.09
    elder
    0.09
    icity
    0.09
    folio
    0.09
    mdi
    0.08
    fce
    0.08
    quoi
    0.08
    imi
    0.08
    imet
    0.08
    Activations Density 0.194%

    No Known Activations