© 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. 55744
    Prev
    Next
    INDEX
    Explanations

    works fine

    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
    .hu
    -0.08
    -handler
    -0.08
     stos
    -0.08
     Fond
    -0.08
    lu
    -0.07
    adar
    -0.07
     Barrett
    -0.07
    lando
    -0.07
     served
    -0.07
    主
    -0.07
    POSITIVE LOGITS
     Reno
    0.09
    ashi
    0.08
    rotch
    0.08
    arel
    0.08
    apo
    0.08
     ung
    0.08
    midd
    0.08
    aset
    0.08
     recruiting
    0.08
     thoroughly
    0.08
    Activations Density 0.075%

    No Known Activations