© 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. 2842
    Prev
    Next
    INDEX
    Explanations

    repeatedly or occasionally

    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
     already
    -0.08
    uit
    -0.07
     imminent
    -0.07
     Overnight
    -0.07
     afterwards
    -0.07
     immediately
    -0.07
     immediate
    -0.07
    ckt
    -0.06
    Timeline
    -0.06
    atories
    -0.06
    POSITIVE LOGITS
     occasionally
    0.30
     consistently
    0.29
     occasional
    0.27
     Occasionally
    0.26
     frequently
    0.26
     repeatedly
    0.24
     regularly
    0.24
     periodically
    0.24
     whenever
    0.23
     always
    0.23
    Activations Density 0.734%

    No Known Activations