© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    text-align

    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
    ouden
    -0.08
     rep
    -0.07
     Moss
    -0.07
    zy
    -0.07
     allegedly
    -0.07
    jem
    -0.07
     Cam
    -0.07
     Rep
    -0.06
     pat
    -0.06
     repl
    -0.06
    POSITIVE LOGITS
    LAS
    0.10
     grav
    0.10
    oenix
    0.10
    enta
    0.09
    oppers
    0.09
    aggi
    0.09
     Pierce
    0.09
     Prayer
    0.09
    ULA
    0.09
     Lad
    0.09
    Activations Density 0.015%

    No Known Activations