© 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. 61946
    Prev
    Next
    INDEX
    Explanations

    in conjunction with

    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
     Plaza
    -0.10
    esch
    -0.09
    ashing
    -0.09
    agu
    -0.09
    lic
    -0.08
     Prof
    -0.08
    ün
    -0.08
    ting
    -0.07
    prof
    -0.07
     informat
    -0.07
    POSITIVE LOGITS
    urv
    0.10
    ware
    0.09
    onal
    0.09
    antium
    0.09
     çok
    0.09
    plorer
    0.09
    acre
    0.09
    icles
    0.09
     stir
    0.08
    Equality
    0.08
    Activations Density 0.007%

    No Known Activations