© 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. 54586
    Prev
    Next
    INDEX
    Explanations

    for a duration

    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
    erg
    -0.09
     intensive
    -0.08
     assisted
    -0.08
     Chatt
    -0.08
    Kat
    -0.08
     intens
    -0.08
     ab
    -0.08
     daily
    -0.08
     fortn
    -0.08
     Transportation
    -0.08
    POSITIVE LOGITS
    ncy
    0.09
    .Clock
    0.09
    argent
    0.09
    aghan
    0.08
    /to
    0.08
    ôn
    0.08
    geries
    0.08
     Pra
    0.08
     próp
    0.08
    =target
    0.08
    Activations Density 0.028%

    No Known Activations