© 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. 8887
    Prev
    Next
    INDEX
    Explanations

    limitation of use

    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
    uga
    -0.11
    aga
    -0.08
     Stranger
    -0.08
    orgen
    -0.07
    eder
    -0.07
     Rouge
    -0.07
     {.
    -0.07
     nad
    -0.07
    anj
    -0.07
     civilian
    -0.07
    POSITIVE LOGITS
     otherwise
    0.12
     confidently
    0.12
     ambitious
    0.11
    ivan
    0.10
    iline
    0.10
    .tom
    0.10
     :(
    0.10
    jac
    0.10
     safely
    0.10
     Deborah
    0.10
    Activations Density 0.407%

    No Known Activations