© 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. 3511
    Prev
    Next
    INDEX
    Explanations

    time, money, and effort

    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
    olid
    -0.08
    ural
    -0.08
    URAL
    -0.08
    caf
    -0.07
    -vis
    -0.07
     Nobel
    -0.07
    .fig
    -0.07
    mac
    -0.07
     Grace
    -0.07
     Oswald
    -0.07
    POSITIVE LOGITS
     effort
    0.16
     efforts
    0.12
     painstaking
    0.12
     Spit
    0.11
     invested
    0.10
     wasted
    0.10
    onium
    0.09
     investment
    0.09
     investments
    0.09
     sunk
    0.09
    Activations Density 0.194%

    No Known Activations