© 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. 8944
    Prev
    Next
    INDEX
    Explanations

    lupus erythematosus

    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
    HR
    -0.10
     swallow
    -0.09
    -fashion
    -0.09
     prob
    -0.09
    .must
    -0.09
    award
    -0.09
     bubbles
    -0.09
     mechanically
    -0.09
     provoked
    -0.09
    defs
    -0.09
    POSITIVE LOGITS
     astr
    0.07
    mez
    0.07
     privile
    0.07
    entiful
    0.07
    erti
    0.07
     pregnant
    0.07
    birthdate
    0.07
     handguns
    0.07
    ylon
    0.07
    .Messaging
    0.07
    Activations Density 0.534%

    No Known Activations