© 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. 8803
    Prev
    Next
    INDEX
    Explanations

    note: if or javascript

    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
    åĬ
    -0.09
     TBD
    -0.09
     hopefully
    -0.08
    ios
    -0.08
    onas
    -0.08
    adan
    -0.08
     eternity
    -0.07
     expans
    -0.07
    Ãĸ
    -0.07
     arg
    -0.07
    POSITIVE LOGITS
     Scre
    0.09
    prefix
    0.09
     Whilst
    0.09
     Bran
    0.09
    >this
    0.09
     While
    0.09
     Sylv
    0.08
    indsight
    0.08
     while
    0.08
     squat
    0.08
    Activations Density 0.118%

    No Known Activations