© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 13
    Prev
    Next
    INDEX
    Explanations

    music credits and roles

    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
    —which
    -0.11
    .',
    -0.11
    ...↵↵↵
    -0.11
    —that
    -0.11
    —and
    -0.11
     rather
    -0.10
    ,the
    -0.10
    .",
    -0.09
    COPY
    -0.09
    .↵↵↵↵↵↵
    -0.09
    POSITIVE LOGITS
    ³³³³³³³³
    0.13
     &
    0.12
     Various
    0.11
     ()↵
    0.10
    :
    0.10
    ³³³³
    0.09
     unspecified
    0.09
    ento
    0.09
     __________________↵↵
    0.09
     approx
    0.09
    Activations Density 2.932%

    No Known Activations