© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2719
    Prev
    Next
    INDEX
    Explanations

    ease and efficiency

    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
     abandon
    -0.09
     moderation
    -0.09
    fdf
    -0.09
     santa
    -0.09
     impactful
    -0.08
    DA
    -0.08
    Santa
    -0.08
    uje
    -0.08
    @if
    -0.08
     Riders
    -0.08
    POSITIVE LOGITS
     quicker
    0.14
     efficiently
    0.13
     quickest
    0.13
     exped
    0.12
     easier
    0.12
     Ease
    0.12
     ease
    0.12
     easiest
    0.12
     quickly
    0.11
     swiftly
    0.11
    Activations Density 0.757%

    No Known Activations