© 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. 8603
    Prev
    Next
    INDEX
    Explanations

    made from, in the image

    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
    vé
    -0.08
     sud
    -0.07
    ilate
    -0.07
     interceptor
    -0.07
    nas
    -0.07
    orne
    -0.07
    ever
    -0.07
     sur
    -0.07
    -padding
    -0.07
    464
    -0.07
    POSITIVE LOGITS
    sembl
    0.10
    axter
    0.10
     exercise
    0.09
     Pig
    0.09
    ixa
    0.09
    agli
    0.09
     erm
    0.09
    emia
    0.09
     Exercise
    0.09
    elda
    0.08
    Activations Density 0.924%

    No Known Activations