© 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. 57820
    Prev
    Next
    INDEX
    Explanations

    contrast introducing clause

    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
    unger
    -0.11
    anske
    -0.11
    ld
    -0.11
    ñas
    -0.11
    ird
    -0.10
     Patty
    -0.10
    andel
    -0.10
    hs
    -0.10
    ieber
    -0.10
    agit
    -0.10
    POSITIVE LOGITS
    (Of
    0.06
     hav
    0.06
     wh
    0.06
     Corm
    0.06
     analys
    0.06
    ANTA
    0.06
    ASA
    0.05
     start
    0.05
     Borrow
    0.05
    tap
    0.05
    Activations Density 0.279%

    No Known Activations