© 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. 53714
    Prev
    Next
    INDEX
    Explanations

    attribute = "type"

    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
    emm
    -0.09
    edia
    -0.09
     governed
    -0.07
    ène
    -0.07
     Stevenson
    -0.07
    ody
    -0.07
    eland
    -0.07
     fel
    -0.07
    pool
    -0.07
    ishi
    -0.07
    POSITIVE LOGITS
    orks
    0.10
     Dro
    0.09
     Wer
    0.09
     anth
    0.09
    wang
    0.09
    aris
    0.09
    wer
    0.09
     wee
    0.09
     å¼
    0.08
     Phillip
    0.08
    Activations Density 0.006%

    No Known Activations