© 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. 8891
    Prev
    Next
    INDEX
    Explanations

    By contrast, by comparison

    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
     fellow
    -0.08
    ichi
    -0.08
     noting
    -0.08
    uent
    -0.08
    aret
    -0.08
     gint
    -0.08
     Primitive
    -0.08
     calls
    -0.07
    aminer
    -0.07
    jit
    -0.07
    POSITIVE LOGITS
     contrast
    0.13
     definition
    0.11
     extension
    0.11
     far
    0.10
     comparison
    0.10
    rd
    0.10
    ť
    0.09
    waters
    0.09
     FAR
    0.09
    arda
    0.09
    Activations Density 0.093%

    No Known Activations