© 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. 8250
    Prev
    Next
    INDEX
    Explanations

    data collection and updates

    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
     brainstorm
    -0.11
    ella
    -0.10
    decor
    -0.10
    /examples
    -0.10
     hypo
    -0.10
    signature
    -0.09
    /topics
    -0.09
     theories
    -0.09
     theor
    -0.09
    /watch
    -0.09
    POSITIVE LOGITS
     completeness
    0.13
     effort
    0.12
     Updating
    0.12
     painstaking
    0.12
     update
    0.12
     collection
    0.11
     compilation
    0.11
     efforts
    0.10
     quality
    0.10
     updates
    0.10
    Activations Density 0.336%

    No Known Activations