© 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. 8779
    Prev
    Next
    INDEX
    Explanations

    automatized/reports/phantom/cone/flash/7-inch/camping/server/pushed/obese

    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
    acer
    -0.08
    usk
    -0.08
     Jeh
    -0.08
     bonds
    -0.08
    adic
    -0.08
    bson
    -0.08
     Xunit
    -0.07
     vib
    -0.07
    disposed
    -0.07
     backwards
    -0.07
    POSITIVE LOGITS
     merely
    0.10
    awah
    0.10
     aqu
    0.09
    RIX
    0.09
    falls
    0.09
     already
    0.09
    UCT
    0.08
     pro
    0.08
    rix
    0.08
    indle
    0.08
    Activations Density 0.750%

    No Known Activations