© 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. 58850
    Prev
    Next
    INDEX
    Explanations

    religious texts and singing

    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
     Wald
    -0.08
    urb
    -0.07
     Flavor
    -0.07
     Transition
    -0.07
    urt
    -0.07
    eras
    -0.07
    ror
    -0.07
    arp
    -0.07
     unb
    -0.06
    argent
    -0.06
    POSITIVE LOGITS
     smarty
    0.11
    DER
    0.11
    abar
    0.10
    ’B
    0.09
     nett
    0.09
     Verd
    0.09
     Nations
    0.09
     Sing
    0.09
     dib
    0.09
     scoring
    0.09
    Activations Density 0.028%

    No Known Activations