© 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. 54562
    Prev
    Next
    INDEX
    Explanations

    then followed by an action

    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
     Ready
    -0.09
    then
    -0.09
     subsequently
    -0.09
     thereafter
    -0.09
     then
    -0.09
    Ready
    -0.08
     ultimately
    -0.08
    THEN
    -0.08
     Staples
    -0.08
    yal
    -0.08
    POSITIVE LOGITS
    andalone
    0.11
     counters
    0.10
     ADM
    0.09
     repeated
    0.09
    .unwrap
    0.09
     clearTimeout
    0.09
    unas
    0.09
    calls
    0.09
     Sav
    0.09
     refuge
    0.09
    Activations Density 0.041%

    No Known Activations