© 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. 8072
    Prev
    Next
    INDEX
    Explanations

    return statements

    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
     Wass
    -0.08
    dam
    -0.08
     lé
    -0.08
    emann
    -0.08
     Dorm
    -0.07
    İ
    -0.07
    oro
    -0.07
    fel
    -0.07
     Vance
    -0.07
    aso
    -0.07
    POSITIVE LOGITS
     snapchat
    0.09
     (*)
    0.09
    .rs
    0.09
    asy
    0.09
     latter
    0.09
    erva
    0.09
     shm
    0.09
    rl
    0.09
    .cwd
    0.09
    andr
    0.08
    Activations Density 0.101%

    No Known Activations