© 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. 54912
    Prev
    Next
    INDEX
    Explanations

    following a noun

    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
    ity
    -0.09
     they
    -0.09
    pace
    -0.08
     vess
    -0.08
     CERT
    -0.08
    soever
    -0.08
     Warn
    -0.08
    ennen
    -0.08
     Hess
    -0.08
    thon
    -0.08
    POSITIVE LOGITS
     Grim
    0.09
    oda
    0.09
    IT
    0.08
    0.08
    recommend
    0.08
    ider
    0.08
     Emerson
    0.08
    cen
    0.08
    elt
    0.08
    itz
    0.08
    Activations Density 0.018%

    No Known Activations