© 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. 54066
    Prev
    Next
    INDEX
    Explanations

    resizing or expanding capacity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Mouth
    -0.10
     sund
    -0.10
    oldem
    -0.10
     blind
    -0.09
    avin
    -0.09
     gorge
    -0.09
     Nose
    -0.09
     Vand
    -0.09
    .cgi
    -0.09
     Subtract
    -0.09
    POSITIVE LOGITS
     expansions
    0.12
     expansion
    0.10
     Expansion
    0.10
    Expansion
    0.09
     growth
    0.09
     Growth
    0.08
    expand
    0.08
     expand
    0.08
    inaire
    0.08
     underlying
    0.08
    Activations Density 0.014%

    No Known Activations