© 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. 4988
    Prev
    Next
    INDEX
    Explanations

    `.cpp` syntax or code tokens

    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
     simultaneous
    -0.09
    LEAN
    -0.09
     simultaneously
    -0.09
     neighb
    -0.08
     ev
    -0.08
    HP
    -0.08
     concurrently
    -0.08
     stup
    -0.07
    erties
    -0.07
    entine
    -0.07
    POSITIVE LOGITS
     itself
    0.14
     proper
    0.11
     Proper
    0.10
     Greene
    0.08
    gary
    0.08
    .oracle
    0.08
    BufferSize
    0.08
     Dies
    0.08
     Vit
    0.08
    acob
    0.08
    Activations Density 0.385%

    No Known Activations