© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57051
    Prev
    Next
    INDEX
    Explanations

    event held on

    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
    nist
    -0.08
     crowds
    -0.08
     guests
    -0.08
    zon
    -0.07
    idge
    -0.07
    azi
    -0.07
    аж
    -0.07
     Tail
    -0.07
    neg
    -0.07
     Visitors
    -0.07
    POSITIVE LOGITS
    .hy
    0.11
     lại
    0.10
    egasus
    0.09
     hy
    0.09
    ress
    0.09
    apt
    0.09
    Callable
    0.09
    AWN
    0.09
    Surname
    0.09
    (now
    0.09
    Activations Density 0.031%

    No Known Activations