© 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. 57798
    Prev
    Next
    INDEX
    Explanations

    not in dispute, motion, claiming, questioning

    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
    rosse
    -0.09
    "use
    -0.09
    ooks
    -0.09
    loser
    -0.08
    Synopsis
    -0.08
     nothing
    -0.08
     conclus
    -0.08
    lichkeit
    -0.08
    ardi
    -0.08
    atest
    -0.08
    POSITIVE LOGITS
     blunt
    0.09
     Folk
    0.09
     Friedman
    0.08
    aml
    0.08
     sane
    0.08
    ural
    0.08
    -il
    0.08
    amy
    0.08
    leigh
    0.08
     Zoo
    0.08
    Activations Density 0.004%

    No Known Activations