© 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. 8711
    Prev
    Next
    INDEX
    Explanations

    new attribute

    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
     Mull
    -0.09
     Berger
    -0.08
    iger
    -0.08
     Scientific
    -0.08
     Herman
    -0.08
    Asked
    -0.07
     Slate
    -0.07
     slice
    -0.07
    ENU
    -0.07
    /java
    -0.07
    POSITIVE LOGITS
     null
    0.13
     parenthesis
    0.10
    null
    0.09
    ubar
    0.09
    =null
    0.09
     Null
    0.08
    .setUp
    0.08
    etch
    0.08
    medi
    0.08
    agram
    0.08
    Activations Density 0.065%

    No Known Activations