© 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. 58945
    Prev
    Next
    INDEX
    Explanations

    inner product or kernel

    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
     décou
    -0.11
    thood
    -0.11
    +xml
    -0.11
    UF
    -0.10
    ema
    -0.10
    .Area
    -0.10
     trat
    -0.10
     interstate
    -0.10
    .nih
    -0.10
    tol
    -0.10
    POSITIVE LOGITS
    mond
    0.07
     Poz
    0.07
     brief
    0.07
     extractor
    0.07
     double
    0.07
    olls
    0.07
     trainable
    0.07
     Extras
    0.06
    erman
    0.06
     Venice
    0.06
    Activations Density 0.020%

    No Known Activations