© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1554
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    wal
    -0.11
     Small
    -0.09
    +-+-
    -0.09
     doubt
    -0.09
     Más
    -0.08
     Period
    -0.08
     pat
    -0.08
    irs
    -0.08
    bet
    -0.08
     Magn
    -0.08
    POSITIVE LOGITS
     per
    0.18
    /kg
    0.12
    _per
    0.11
    /sec
    0.11
     equivalents
    0.10
    emens
    0.10
    /year
    0.10
    _PER
    0.10
     equiv
    0.09
    /mL
    0.09
    Activations Density 0.706%

    No Known Activations