© 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. 53823
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     "
    -0.10
     *"
    -0.08
    ..."
    -0.08
     "...
    -0.08
    âĢİ
    -0.08
    ["
    -0.07
    -"
    -0.07
     Bud
    -0.07
     '
    -0.07
    ...↵
    -0.07
    POSITIVE LOGITS
     youre
    0.11
     Womens
    0.11
    ,!
    0.10
    ;!
    0.10
     dont
    0.10
     Wand
    0.10
    ,.
    0.10
     Swinger
    0.10
     Dont
    0.10
    laden
    0.10
    Activations Density 0.090%

    No Known Activations