© 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. 57382
    Prev
    Next
    INDEX
    Explanations

    units of measurement and time

    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
     Gren
    -0.09
    .Des
    -0.09
    teil
    -0.09
    pars
    -0.09
    inho
    -0.09
    rang
    -0.09
     Stateless
    -0.09
    agar
    -0.09
    PELL
    -0.09
    pyx
    -0.09
    POSITIVE LOGITS
     revert
    0.08
    cket
    0.08
     tap
    0.08
     Flash
    0.07
    wich
    0.07
    atable
    0.07
     rever
    0.07
     reverted
    0.07
    -ed
    0.07
    combination
    0.07
    Activations Density 0.001%

    No Known Activations