© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61170
    Prev
    Next
    INDEX
    Explanations

    awesome

    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
    Negative Logits
    ily
    -0.12
    ingly
    -0.10
    ist
    -0.09
    ably
    -0.09
     bump
    -0.09
    Smooth
    -0.09
     luk
    -0.09
     smooth
    -0.09
    erb
    -0.09
    رÙĪ
    -0.08
    POSITIVE LOGITS
    adge
    0.11
    enschaft
    0.10
    ool
    0.09
    nowledge
    0.09
    ANE
    0.09
    ody
    0.09
    ROS
    0.09
    alley
    0.09
    rir
    0.09
    dds
    0.09
    Activations Density 0.011%

    No Known Activations