© 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. 8753
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     taller
    -0.09
     (>
    -0.09
     monster
    -0.09
    Species
    -0.09
    species
    -0.08
    rico
    -0.08
    -spec
    -0.08
    -android
    -0.08
    rial
    -0.08
    cap
    -0.08
    POSITIVE LOGITS
    ä½
    0.11
     lower
    0.11
     Lowest
    0.10
     Lower
    0.10
     below
    0.10
     (<
    0.09
     lowers
    0.09
    kus
    0.09
     beneath
    0.09
     stri
    0.09
    Activations Density 0.224%

    No Known Activations