© 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. 4916
    Prev
    Next
    INDEX
    Explanations

    cover artwork/art

    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
     br
    -0.09
    lingen
    -0.09
     Celebrity
    -0.09
    _struct
    -0.09
    ObjectName
    -0.09
    (strict
    -0.09
     Crowd
    -0.09
     Wen
    -0.09
    bron
    -0.09
     Ning
    -0.09
    POSITIVE LOGITS
    /banner
    0.09
    /title
    0.09
    ef
    0.08
    deep
    0.08
    okin
    0.08
     ere
    0.08
     deep
    0.08
    ium
    0.08
     ep
    0.08
     Deep
    0.08
    Activations Density 0.279%

    No Known Activations