© 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. 57247
    Prev
    Next
    INDEX
    Explanations

    slow and passive states

    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
     vigorous
    -0.11
     swift
    -0.11
     UIP
    -0.10
    repid
    -0.10
     tearing
    -0.10
     energ
    -0.10
     exhilar
    -0.10
     volatile
    -0.10
    /open
    -0.09
     flush
    -0.09
    POSITIVE LOGITS
     slower
    0.20
     slow
    0.20
     slowing
    0.20
     slowed
    0.19
     slows
    0.18
     stagn
    0.17
     Slow
    0.17
    slow
    0.17
     static
    0.17
     passive
    0.17
    Activations Density 0.121%

    No Known Activations