© 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. 54760
    Prev
    Next
    INDEX
    Explanations

    ratings out of 5

    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
    orders
    -0.10
     incumb
    -0.10
     curs
    -0.09
    ';↵↵↵↵
    -0.09
    č↵↵
    -0.09
    isle
    -0.09
    OTH
    -0.09
    asty
    -0.09
    isode
    -0.09
     skate
    -0.09
    POSITIVE LOGITS
     hub
    0.08
    Md
    0.08
     aggregator
    0.08
     zb
    0.08
    Prog
    0.07
     weighted
    0.07
     Sheridan
    0.07
     hostages
    0.07
     ICollection
    0.07
    .FileSystem
    0.07
    Activations Density 0.003%

    No Known Activations