© 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. 4816
    Prev
    Next
    INDEX
    Explanations

    appears

    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
    Ø·
    -0.10
     takeaway
    -0.09
     cere
    -0.09
    enders
    -0.08
    etas
    -0.08
    aires
    -0.08
    ordo
    -0.08
    afe
    -0.08
    aire
    -0.08
    .Scan
    -0.08
    POSITIVE LOGITS
    ants
    0.10
    antly
    0.10
    mant
    0.09
    ances
    0.09
     Ecc
    0.08
     countless
    0.08
    assing
    0.08
     suddenly
    0.08
     Naturally
    0.08
     prominently
    0.08
    Activations Density 0.117%

    No Known Activations