© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    separators

    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
    olo
    -0.07
    :
    -0.07
    ees
    -0.07
    -0.07
    eries
    -0.07
    erie
    -0.07
    ↵
    -0.07
    umm
    -0.06
    uality
    -0.06
     glob
    -0.06
    POSITIVE LOGITS
    .more
    0.11
    quoi
    0.11
     vog
    0.10
    andes
    0.10
    ————————
    0.10
    inand
    0.10
    vos
    0.10
    å»
    0.10
    .Sum
    0.10
    ncia
    0.10
    Activations Density 0.015%

    No Known Activations