© 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. 53941
    Prev
    Next
    INDEX
    Explanations

    SQL ORM code

    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
    äºĭ
    -0.08
    sea
    -0.08
    Squared
    -0.08
    soever
    -0.07
    miss
    -0.07
     obr
    -0.07
    atch
    -0.07
     sealed
    -0.07
    framework
    -0.07
     Amen
    -0.07
    POSITIVE LOGITS
    иÑĤелÑĮ
    0.10
    rollo
    0.09
    vero
    0.09
    ,),↵
    0.09
    ãģĵãĤĵ
    0.09
    .opens
    0.09
     SENT
    0.09
     Ended
    0.09
     pred
    0.09
     Ends
    0.09
    Activations Density 0.008%

    No Known Activations