© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    -induced causes

    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
    enty
    -0.09
    awn
    -0.08
    fully
    -0.08
    woke
    -0.08
     erg
    -0.08
     Pee
    -0.08
     bast
    -0.08
    ias
    -0.08
    Marshal
    -0.08
    olk
    -0.08
    POSITIVE LOGITS
    inctions
    0.09
    noc
    0.08
     Walt
    0.08
    óm
    0.08
     depend
    0.08
    nist
    0.08
     cris
    0.08
    itr
    0.08
    allen
    0.08
    ERIC
    0.08
    Activations Density 0.125%

    No Known Activations