© 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. 55186
    Prev
    Next
    INDEX
    Explanations

    cd followed by ots

    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
    reed
    -0.09
    wal
    -0.08
    umo
    -0.08
     laz
    -0.08
    colo
    -0.08
    aad
    -0.08
    ando
    -0.07
     Brut
    -0.07
     cancelling
    -0.07
    ackle
    -0.07
    POSITIVE LOGITS
    Filed
    0.10
    ed
    0.09
    Ñģл
    0.09
     tack
    0.09
    iter
    0.09
    eson
    0.09
    ÑĨа
    0.08
    ots
    0.08
     euros
    0.08
     squeeze
    0.08
    Activations Density 0.001%

    No Known Activations