© 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. 61199
    Prev
    Next
    INDEX
    Explanations

    Qt Toolkit

    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
    endor
    -0.10
    anno
    -0.08
    iel
    -0.08
     mil
    -0.08
    cen
    -0.08
     pouch
    -0.08
     Literal
    -0.08
     protagon
    -0.07
    fo
    -0.07
    aces
    -0.07
    POSITIVE LOGITS
     escalating
    0.08
    play
    0.08
    bc
    0.08
    Cho
    0.08
    .Net
    0.08
    tic
    0.08
     Whe
    0.08
    íĦ°
    0.08
     Way
    0.08
    :Array
    0.08
    Activations Density 0.002%

    No Known Activations