© 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. 53940
    Prev
    Next
    INDEX
    Explanations

    large quantity of

    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
     ways
    -0.10
     jel
    -0.10
    ли
    -0.10
     lawy
    -0.09
     theoretically
    -0.09
    ere
    -0.09
     dozen
    -0.09
     Oaks
    -0.09
     Segment
    -0.09
     dozens
    -0.08
    POSITIVE LOGITS
    atu
    0.09
     Merr
    0.08
    /small
    0.08
    office
    0.08
    RH
    0.07
    ÑĢаÐ
    0.07
     éc
    0.07
     tenÃŃa
    0.07
    kom
    0.07
    .rs
    0.07
    Activations Density 0.042%

    No Known Activations