© 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. 3579
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation/text

    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
     rot
    -0.08
     Inject
    -0.08
    Trivia
    -0.08
     Hue
    -0.08
    ople
    -0.08
    OMET
    -0.08
     poi
    -0.07
     naked
    -0.07
    -Fi
    -0.07
     Rot
    -0.07
    POSITIVE LOGITS
    Remaining
    0.09
    ped
    0.09
    usband
    0.09
     Wonderland
    0.09
     remaining
    0.09
    chan
    0.09
     Rico
    0.09
    GY
    0.08
    peng
    0.08
    =view
    0.08
    Activations Density 0.005%

    No Known Activations