© 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. 61968
    Prev
    Next
    INDEX
    Explanations

    structural components and parts

    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
     respawn
    -0.08
     laz
    -0.08
    dy
    -0.08
    eyed
    -0.08
    ute
    -0.08
    Targets
    -0.08
     ìĺ
    -0.08
    azines
    -0.08
    -at
    -0.08
    ä½į
    -0.08
    POSITIVE LOGITS
     emb
    0.09
    eness
    0.08
     Native
    0.08
    aden
    0.08
    ikes
    0.08
     wa
    0.08
     same
    0.07
     blending
    0.07
     Brett
    0.07
    mith
    0.07
    Activations Density 0.011%

    No Known Activations