© 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. 689
    Prev
    Next
    INDEX
    Explanations

    studies on or about

    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
    eu
    -0.10
    erb
    -0.09
     Reporter
    -0.09
     Conserv
    -0.09
     usual
    -0.09
    hv
    -0.09
    oref
    -0.08
     trimest
    -0.08
     organis
    -0.08
    acre
    -0.08
    POSITIVE LOGITS
     how
    0.15
    how
    0.11
     interactions
    0.10
     “[
    0.10
    0.09
    /how
    0.09
     cómo
    0.09
     âĢķ
    0.09
     behalf
    0.09
     aspects
    0.09
    Activations Density 4.120%

    No Known Activations