© 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. 5029
    Prev
    Next
    INDEX
    Explanations

    script type="text/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
    oday
    -0.10
    iken
    -0.10
    orate
    -0.09
     bust
    -0.09
    oord
    -0.09
     Isa
    -0.09
    VERAGE
    -0.09
    legg
    -0.08
     PIX
    -0.08
    atype
    -0.08
    POSITIVE LOGITS
    اب
    0.09
     forgotten
    0.09
    (es
    0.08
    emens
    0.08
     tap
    0.08
     forgot
    0.08
     afr
    0.08
     redeem
    0.08
    tick
    0.08
    hel
    0.07
    Activations Density 0.029%

    No Known Activations