© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    executed, implementation, actual

    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
    _reporting
    -0.09
    Registry
    -0.09
     registry
    -0.08
     stool
    -0.08
     regist
    -0.08
    pers
    -0.08
     Dia
    -0.08
    ngen
    -0.08
     Jah
    -0.08
     economist
    -0.08
    POSITIVE LOGITS
     implementation
    0.17
     Actual
    0.16
     execution
    0.16
     Implementation
    0.16
     actual
    0.15
     implement
    0.15
     IMPLEMENT
    0.14
     execute
    0.14
     Implement
    0.13
    Actual
    0.13
    Activations Density 0.623%

    No Known Activations