© 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. 58774
    Prev
    Next
    INDEX
    Explanations

    world around us

    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
     transformation
    -0.07
    ê¸
    -0.07
     faint
    -0.07
     slur
    -0.07
    uri
    -0.07
    ymes
    -0.07
    Ч
    -0.07
     transformative
    -0.07
    ç¾
    -0.06
     shopping
    -0.06
    POSITIVE LOGITS
     поÑĢ
    0.10
     Sanford
    0.10
    ouv
    0.10
     wild
    0.10
    cesso
    0.10
    hr
    0.10
     Haz
    0.10
    Äĩe
    0.10
    stance
    0.10
     cosmos
    0.10
    Activations Density 0.065%

    No Known Activations