© 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. 702
    Prev
    Next
    INDEX
    Explanations

    machine learning algorithms and models

    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
     numbered
    -0.11
    Formatting
    -0.11
     doubling
    -0.11
     bare
    -0.10
     congr
    -0.10
     bum
    -0.10
     fabrication
    -0.10
     cleared
    -0.10
     clearance
    -0.10
     numbering
    -0.10
    POSITIVE LOGITS
     algorithms
    0.22
     algorithm
    0.21
     Algorithm
    0.16
     Algorithms
    0.15
     models
    0.13
    Algorithm
    0.13
     penal
    0.13
     optim
    0.12
     Bayesian
    0.12
     robust
    0.12
    Activations Density 1.985%

    No Known Activations