© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8317
    Prev
    Next
    INDEX
    Explanations

    would have, would turn, had not

    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
    Negative Logits
    antu
    -0.09
    asan
    -0.09
    uche
    -0.09
    eno
    -0.09
    yc
    -0.09
    UST
    -0.08
    un
    -0.08
    idi
    -0.08
    ells
    -0.08
    enco
    -0.08
    POSITIVE LOGITS
     Would
    0.13
     would
    0.12
     had
    0.12
     wouldn
    0.12
    Would
    0.12
    Had
    0.11
    had
    0.11
    would
    0.11
     Had
    0.09
     hindsight
    0.09
    Activations Density 0.122%

    No Known Activations