© 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. 54936
    Prev
    Next
    INDEX
    Explanations

    perforated

    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
    freeze
    -0.11
    fully
    -0.09
    -0.09
    ieux
    -0.09
    OP
    -0.09
    cut
    -0.09
    kle
    -0.09
     froze
    -0.09
    UE
    -0.09
    onas
    -0.09
    POSITIVE LOGITS
    sent
    0.09
     Err
    0.07
     Ness
    0.07
    thed
    0.07
     perd
    0.07
    .rs
    0.07
     encompass
    0.07
    é©
    0.07
    arg
    0.07
     Gund
    0.07
    Activations Density 0.002%

    No Known Activations