© 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. 2483
    Prev
    Next
    INDEX
    Explanations

    separator for numbers and code snippets

    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
    ives
    -0.10
    ive
    -0.09
    uhl
    -0.09
    arge
    -0.09
     aver
    -0.08
     em
    -0.08
    compression
    -0.08
    isure
    -0.08
     sequ
    -0.08
     seams
    -0.08
    POSITIVE LOGITS
    çľģ
    0.09
     crude
    0.08
    bootstrap
    0.08
     neutr
    0.08
    etro
    0.08
    Misc
    0.08
    abay
    0.08
    /local
    0.07
     bootstrap
    0.07
     decorator
    0.07
    Activations Density 0.695%

    No Known Activations