© 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. 54658
    Prev
    Next
    INDEX
    Explanations

    google.golang.org/genproto/googleapis/api/annotations", the responseerr importimport Model

    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
    nces
    -0.07
     AVR
    -0.07
     acre
    -0.07
     inquire
    -0.07
     Concurrent
    -0.07
    -community
    -0.07
     enquiry
    -0.07
    clide
    -0.07
    .Qu
    -0.07
     NC
    -0.07
    POSITIVE LOGITS
    alach
    0.10
    gn
    0.10
    omet
    0.10
     prov
    0.09
     swing
    0.09
    Equip
    0.09
    ’on
    0.09
     Epstein
    0.09
    FETCH
    0.09
     escal
    0.09
    Activations Density 0.002%

    No Known Activations