© 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. 8814
    Prev
    Next
    INDEX
    Explanations

    function execution based on conditions

    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
     Awards
    -0.09
     steer
    -0.09
    unal
    -0.09
     pours
    -0.08
    åľŁ
    -0.08
    mand
    -0.08
     Deluxe
    -0.08
     initiated
    -0.08
     recycle
    -0.08
     progress
    -0.08
    POSITIVE LOGITS
     permanently
    0.13
     operational
    0.12
     lifelong
    0.10
     intercept
    0.10
     tested
    0.10
     capability
    0.10
     learnt
    0.10
     capable
    0.10
     learned
    0.10
     callable
    0.09
    Activations Density 0.683%

    No Known Activations