© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2494
    Prev
    Next
    INDEX
    Explanations

    when material subjected to stress or temperature

    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
     rapp
    -0.09
     destruct
    -0.08
     unreliable
    -0.08
    /people
    -0.08
    kek
    -0.08
    fir
    -0.08
    tec
    -0.08
     eventual
    -0.08
     inf
    -0.08
    pekt
    -0.08
    POSITIVE LOGITS
     exposed
    0.11
    Exposed
    0.10
     positioned
    0.10
     nearby
    0.09
    iego
    0.09
     conduc
    0.09
     rubbing
    0.09
    578
    0.09
     excited
    0.09
     sensitive
    0.09
    Activations Density 0.343%

    No Known Activations