© 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. 54643
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    Ц
    -0.09
    ern
    -0.09
     *,↵
    -0.08
    мен
    -0.08
     gradu
    -0.08
    oder
    -0.08
    eken
    -0.08
    ehen
    -0.08
     Ear
    -0.08
    fuse
    -0.08
    POSITIVE LOGITS
    ])[
    0.10
    atk
    0.09
    yat
    0.09
    itta
    0.08
    inne
    0.08
     circa
    0.08
    locked
    0.08
     lang
    0.08
    ijo
    0.08
    iors
    0.08
    Activations Density 0.002%

    No Known Activations