© 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. 4090
    Prev
    Next
    INDEX
    Explanations

    attribute assignment or declaration

    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
    .stamp
    -0.09
    untime
    -0.09
    -runtime
    -0.08
     runtime
    -0.08
    udi
    -0.07
    burn
    -0.07
    ä»ĺ
    -0.07
    Runtime
    -0.07
    iju
    -0.07
    /hash
    -0.07
    POSITIVE LOGITS
     expected
    0.17
     anticipated
    0.14
     Expected
    0.14
     expect
    0.12
    _expected
    0.12
     predicted
    0.12
     expectation
    0.12
    expected
    0.11
     monitoring
    0.11
    .expected
    0.11
    Activations Density 0.590%

    No Known Activations