© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    unexpected actions

    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
     annually
    -0.14
     weekly
    -0.13
     someday
    -0.13
     yearly
    -0.13
     monthly
    -0.12
     weekend
    -0.12
     overnight
    -0.11
     Overnight
    -0.11
     permanently
    -0.11
     months
    -0.11
    POSITIVE LOGITS
     momentarily
    0.14
     seconds
    0.13
     motion
    0.13
     bystand
    0.11
     nearby
    0.11
     Nearby
    0.10
     distractions
    0.10
     mientras
    0.10
     movements
    0.10
     motions
    0.10
    Activations Density 1.328%

    No Known Activations