© 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. 53762
    Prev
    Next
    INDEX
    Explanations

    state and its attributes (e.g., of, 's)

    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
    sville
    -0.09
    mint
    -0.08
    /content
    -0.08
    aku
    -0.08
    estate
    -0.07
    raf
    -0.07
    owie
    -0.07
     purse
    -0.07
    kest
    -0.07
     Beard
    -0.07
    POSITIVE LOGITS
    ster
    0.11
     endings
    0.10
    ewan
    0.10
     GPLv
    0.10
    elan
    0.10
    gre
    0.09
    assen
    0.09
     Sweat
    0.09
     proceeding
    0.09
    eler
    0.09
    Activations Density 0.025%

    No Known Activations