© 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. 8134
    Prev
    Next
    INDEX
    Explanations

    URL paths and codes

    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
     Wax
    -0.09
     Hale
    -0.09
     wax
    -0.08
    egot
    -0.08
    annon
    -0.08
     miniature
    -0.07
    ÂŃ
    -0.07
    aina
    -0.07
     ÂŃ
    -0.07
    ÃĤ
    -0.07
    POSITIVE LOGITS
     Pied
    0.10
    cis
    0.09
    atar
    0.09
     bö
    0.09
     Grove
    0.08
     Bened
    0.08
     Gui
    0.08
    à¸Ń
    0.08
     Petro
    0.08
     fontFamily
    0.08
    Activations Density 0.330%

    No Known Activations