© 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. 8595
    Prev
    Next
    INDEX
    Explanations

    congressional districts and representatives

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Freak
    -0.10
     Presidential
    -0.10
     EVP
    -0.09
    ateria
    -0.09
    polator
    -0.09
     Sle
    -0.09
     cue
    -0.09
    _HOOK
    -0.08
    -Sah
    -0.08
    erp
    -0.08
    POSITIVE LOGITS
     seat
    0.10
     representation
    0.09
     seats
    0.09
    Seat
    0.09
     newcomers
    0.09
    haps
    0.09
    ourd
    0.08
     Seat
    0.08
     Levin
    0.08
     retiring
    0.08
    Activations Density 0.224%

    No Known Activations