© 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. 58795
    Prev
    Next
    INDEX
    Explanations

    .php files

    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
    ped
    -0.11
    ador
    -0.10
    lass
    -0.09
     Thur
    -0.09
    ZO
    -0.09
    amento
    -0.08
    atal
    -0.08
    pet
    -0.08
    ewood
    -0.08
     Ped
    -0.08
    POSITIVE LOGITS
    ically
    0.11
    lys
    0.11
    azel
    0.08
     Britt
    0.08
    hm
    0.08
    eel
    0.08
    Utc
    0.08
    cock
    0.08
     Listings
    0.08
     Dick
    0.07
    Activations Density 0.006%

    No Known Activations