© 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. 58363
    Prev
    Next
    INDEX
    Explanations

    let d =

    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
    cul
    -0.08
    nda
    -0.07
    ittel
    -0.07
     Serge
    -0.07
    د
    -0.07
    xa
    -0.07
    orc
    -0.07
    istik
    -0.07
     finns
    -0.07
    Ath
    -0.07
    POSITIVE LOGITS
    emit
    0.11
    èī
    0.10
    opr
    0.10
    :len
    0.10
     rolling
    0.10
    quot
    0.10
    emet
    0.10
     cour
    0.09
     Hip
    0.09
     thÃłnh
    0.09
    Activations Density 0.008%

    No Known Activations