© 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. 8691
    Prev
    Next
    INDEX
    Explanations

    123

    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
    ful
    -0.11
    fulness
    -0.10
    liness
    -0.10
    lessly
    -0.09
     ward
    -0.09
    ussy
    -0.09
    NESS
    -0.09
     heck
    -0.08
    fully
    -0.08
    licher
    -0.08
    POSITIVE LOGITS
    ation
    0.10
    ical
    0.10
    zy
    0.10
    ed
    0.10
    lett
    0.09
    rick
    0.09
    oven
    0.09
    ition
    0.09
    iture
    0.08
    thesis
    0.08
    Activations Density 0.120%

    No Known Activations