© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    org

    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
    /__
    -0.09
     dip
    -0.09
    .EventQueue
    -0.08
    utto
    -0.08
     tender
    -0.08
     Marcos
    -0.08
    OPY
    -0.08
     tightly
    -0.08
     Preis
    -0.08
     pylint
    -0.08
    POSITIVE LOGITS
    =T
    0.08
    ìŀħ
    0.08
    .enumer
    0.08
    Į¨
    0.08
    idunt
    0.08
    ohana
    0.08
    ajaran
    0.07
     barr
    0.07
    hlen
    0.07
    (trans
    0.07
    Activations Density 2.340%

    No Known Activations