© 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. 55589
    Prev
    Next
    INDEX
    Explanations

    build tasks

    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
    criptors
    -0.10
    eron
    -0.10
     pieces
    -0.10
    AGON
    -0.10
    hra
    -0.10
    cept
    -0.10
    charts
    -0.10
     patches
    -0.10
    Transactional
    -0.09
    blob
    -0.09
    POSITIVE LOGITS
     prepar
    0.09
     tasks
    0.08
    noon
    0.08
     delegated
    0.07
     activities
    0.07
    allen
    0.07
     sequence
    0.07
     Bere
    0.07
     subcontract
    0.07
    subs
    0.07
    Activations Density 0.020%

    No Known Activations