© 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. 2025
    Prev
    Next
    INDEX
    Explanations

    suffix or ending of a word

    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
    fully
    -0.12
     internals
    -0.10
    lauf
    -0.09
    kok
    -0.09
    edition
    -0.09
    aland
    -0.09
    edly
    -0.09
    ROS
    -0.09
    elian
    -0.09
     underlying
    -0.09
    POSITIVE LOGITS
    ity
    0.22
    ized
    0.22
    ities
    0.20
    ITY
    0.19
    izing
    0.18
    ization
    0.16
    ism
    0.16
    ize
    0.16
    idad
    0.15
    ité
    0.15
    Activations Density 2.925%

    No Known Activations