© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57904
    Prev
    Next
    INDEX
    Explanations

    Welsh people and places

    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
    .kafka
    -0.10
    iable
    -0.09
    agy
    -0.09
    tempt
    -0.09
    nement
    -0.09
     dr
    -0.09
    anium
    -0.09
     Tro
    -0.09
     Cummings
    -0.09
    но
    -0.09
    POSITIVE LOGITS
    es
    0.11
    y
    0.09
    oth
    0.09
    emu
    0.08
    ryn
    0.08
    metric
    0.08
    Ñĭ
    0.08
    o
    0.08
    entities
    0.08
     objective
    0.08
    Activations Density 0.021%

    No Known Activations