© 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. 53925
    Prev
    Next
    INDEX
    Explanations

    round of draft selections

    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
    å¹
    -0.08
     beg
    -0.07
    ienen
    -0.07
    ensch
    -0.07
    ROSS
    -0.07
     Clo
    -0.07
     consec
    -0.07
     Stem
    -0.07
     impression
    -0.07
     attenu
    -0.07
    POSITIVE LOGITS
    ers
    0.14
    rek
    0.09
     liabilities
    0.09
    enes
    0.09
    AIR
    0.09
     marca
    0.09
    lier
    0.09
    ly
    0.09
    rate
    0.09
     zw
    0.09
    Activations Density 0.002%

    No Known Activations