© 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. 61820
    Prev
    Next
    INDEX
    Explanations

    wikipedia or wikipedia

    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
    izin
    -0.08
    inkle
    -0.08
     Punch
    -0.08
     intoxicated
    -0.08
    onte
    -0.08
     ink
    -0.08
    ayo
    -0.08
    aar
    -0.07
    comed
    -0.07
    &e
    -0.07
    POSITIVE LOGITS
     wikipedia
    0.11
     Wikipedia
    0.10
    ê¸Ģ
    0.10
     punct
    0.09
    Wik
    0.09
     blat
    0.09
     Wikimedia
    0.08
     Wik
    0.08
     contr
    0.08
     datab
    0.08
    Activations Density 0.143%

    No Known Activations