© 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. 4059
    Prev
    Next
    INDEX
    Explanations

    **state change, ending, or restoration**

    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
     irre
    -0.11
    uder
    -0.11
     unregister
    -0.10
     abandonment
    -0.10
    lop
    -0.10
     irreversible
    -0.09
    ripp
    -0.09
     qua
    -0.09
     goodbye
    -0.09
     svo
    -0.09
    POSITIVE LOGITS
     back
    0.09
     restored
    0.09
     Back
    0.09
    inson
    0.09
     later
    0.09
     correction
    0.08
     Nap
    0.08
     restoration
    0.08
     afterwards
    0.08
     afterward
    0.08
    Activations Density 0.239%

    No Known Activations