© 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. 57462
    Prev
    Next
    INDEX
    Explanations

    then, once, afterwards

    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
    ognito
    -0.10
    ogle
    -0.10
    Outer
    -0.09
     Outer
    -0.09
    vic
    -0.09
    ®
    -0.09
    Vs
    -0.09
    uard
    -0.09
    inal
    -0.09
    outh
    -0.09
    POSITIVE LOGITS
     once
    0.24
     Once
    0.22
    Once
    0.20
     afterwards
    0.19
    once
    0.19
     afterward
    0.18
     thereafter
    0.17
     subsequently
    0.14
    onces
    0.11
     then
    0.11
    Activations Density 0.195%

    No Known Activations