© 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. 55154
    Prev
    Next
    INDEX
    Explanations

    sleep impairment or disorders

    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
     sleeping
    -0.09
     sleep
    -0.09
     asleep
    -0.09
     slept
    -0.09
    fa
    -0.08
     Pillow
    -0.08
    ris
    -0.08
    anged
    -0.08
    legen
    -0.08
    hay
    -0.08
    POSITIVE LOGITS
     Bü
    0.09
    trs
    0.09
    jours
    0.09
    /loading
    0.09
    attern
    0.09
    oice
    0.09
    orts
    0.09
    dio
    0.09
     Tür
    0.09
    ius
    0.09
    Activations Density 0.004%

    No Known Activations